Runtime Trust By JACK · May 24, 2026 · 8 min read

Provenance chain fracture: when AI agents trust forged evidence

Provenance chain fracture is a runtime attack class where adversaries inject fabricated evidence — forge signatures, timestamps, and audit trails — to make an AI agent's reasoning look grounded when it isn't. Sunglasses v0.2.48 ships five new detection patterns (GLS-PCF-667, GLS-PCF-245 through GLS-PCF-248) covering signed evidence forgery, timestamp injection, and audit trail fabrication.

Agent Workflow Security By JACK · May 23, 2026 · 9 min read

Agentic CI/CD Security: Runtime Trust for AI Coding Agents in Pipelines

AI coding agents turn CI/CD pipelines into promptable runtimes with secrets, shell, MCP tools, packages, and deploy authority. Sunglasses v0.2.47 ships 21 new detection patterns (GLS-AW-106 through GLS-AW-126) in the agent_workflow_security category covering PR comment injection, MCP metadata steering, and package endpoint drift.

Agent Workflow Security By JACK · May 22, 2026 · 8 min read

AI Agent Workflow Security: Every Step Needs an Evidence Contract

The riskiest part of an AI agent workflow is the handoff between steps — what evidence, authority, and state the next action inherits. Sunglasses v0.2.46 ships 21 new detection patterns (GLS-AW-085 through GLS-AW-105) covering freshness asymmetry, summary laundering, scope inflation, and state rehydration in the agent_workflow_security category.

Agent Workflow Security By JACK · May 21, 2026 · 9 min read

AI Agent Telemetry Poisoning: When The Dashboard Lies

AI agents trust dashboards, scorecards, freshness badges, and decision traces — not just prompts. Sunglasses v0.2.45 ships 21 new detection patterns (GLS-AW-064 through GLS-AW-084) covering telemetry poisoning, freshness badge forgery, KPI scorecard substitution, and decision trace approval forgery in the agent_workflow_security category.

Agent Workflow Security By JACK · May 20, 2026 · 10 min read

Managed Agents Are Not Trusted Actions

Managed agents, connectors, MCP apps, per-tool permissions, and audit logs make workflows safer — they still do not decide whether the next already-allowed action should be trusted now. Sunglasses v0.2.44 ships 21 new agent_workflow_security patterns (GLS-AW-043 through GLS-AW-063) covering gap-fill fabrication, verification gate forgery, and plan summary execution drift attacks.

Agent Workflow Security By JACK · May 19, 2026 · 10 min read

AI Agent Security vs AI Usage Control: What Runtime Trust Still Has To Decide

AI usage control and AI governance reduce exposure, but AI agent security still requires a runtime-trust layer that decides whether a live tool call, MCP handoff, callback chain, or outbound request should still be trusted. Sunglasses v0.2.43 ships 700 detection patterns including the agent_workflow_security category targeting exactly this decision layer.

AI Agent Security By JACK · May 18, 2026 · 5 min read

When AI Agent Attacks Stop Looking Theoretical

Three real incidents — Axios npm compromise, Claude Code fake repos, EchoLeak (CVE-2025-32711) — prove AI-adjacent systems are already under attack through trust, distribution, and context. The weapon is not always the content itself. It is the path the system takes after reading it.

Cross-Agent Injection By JACK · May 17, 2026 · 8 min read

Session Boundaries Are Control Boundaries in Agent Systems

Most teams treat session management bugs as web hygiene. In agentic infrastructure, session boundaries are control-plane boundaries for orchestrators, run metadata, connector actions, and execution-adjacent workflows. When post-logout JWTs remain valid (CVE-2025-57735), governance assumptions fail. Covers the cross_agent_injection attack surface (GLS-CAI-710..713) and why low-CVSS session bugs become high-consequence footholds in agent pipelines.

Comparison By JACK · May 16, 2026 · 10 min read

Sunglasses vs Lakera Guard: An Honest Comparison for AI Agent Security Teams

Looking for a Lakera alternative? Sunglasses and Lakera both speak to AI agent security, but they fit different layers. Lakera is a broader commercial AI security platform with enterprise control-plane coverage. Sunglasses is an open-source, local-first filter that inspects prompts, MCP tool text, and repository content before an agent acts on them. This comparison covers scope, open-source access, MCP coverage, and runtime-trust posture so you can pick the right fit — or run both.

Runtime Trust By JACK · May 15, 2026 · 9 min read

Policy Scope Redefinition Is a Runtime-Trust Problem: Why MCP Scope Creep Becomes Unsafe Agent Action

Policy scope redefinition is when later-stage text quietly expands what an AI agent believes it is allowed to do — an appendix that claims to outrank the original policy, a connector note that silently broadens workspace scope. It is distinct from prompt injection: injection attacks influence, scope redefinition attacks authority. Sunglasses introduced the policy_scope_redefinition category early on with GLS-PSR-001, and the latest release expands it with seventeen more patterns (GLS-PSR-580 through GLS-PSR-596).

Supply Chain Security By JACK · May 15, 2026 · 12 min read

The Skill Store Is the New Package Registry — Except Worse

AI agent skill ecosystems are starting to look like package registries from the bad old days of supply-chain compromise — except worse. The attack surface now includes natural-language guidance (SKILL.md, setup instructions, permission narratives) that agents treat as authoritative. Classic code scanning misses the instruction layer. This is workflow deception detection, and most teams are not scanning for it yet.

Agent Workflow Security By JACK · May 13, 2026 · 10 min read

AI Agent Guardrails vs Runtime Trust: Trusted Access Is Not the Last Security Decision

AI agent guardrails reduce exposure and narrow allowed behavior, but they do not finish AI agent security. Sunglasses 0.2.39 ships 12 new agent_workflow_security patterns (GLS-AW-031 through GLS-AW-042) targeting model-routing hijacks, policy scope redefinition, and workflow trust chain manipulation — the exact attack surface guardrails leave open.

Runtime Trust By JACK · May 13, 2026 · 10 min read

Agent Link Safety Is Not Enough: The Runtime-Trust Checks AI Workflows Still Need Before They Act

Link filtering, URL allowlists, redirect controls, and browser isolation narrow where an agent may go — they do not decide whether the workflow should still trust the next callback, redirect, or destination after new context arrives. Sunglasses 0.2.38 ships 11 new tool_output_poisoning patterns (GLS-TOP-621 through GLS-TOP-630, plus GLS-OP-002) targeting forged tool receipts, provenance forgery, redaction drift, and order-dependent trust manipulation — the action-time decisions link safety leaves open.

Threat Analysis By JACK · May 13, 2026 · 11 min read

How To Stop AI Agents From Calling Untrusted Endpoints: Why Allowlists Are Not Enough

Stopping AI agents from calling untrusted endpoints takes more than an allowlist. Sunglasses 0.2.37 ships cross_agent_injection patterns (GLS-CAI-690 through GLS-CAI-704) that cover the outbound-trust gap — forged handoff tickets, capability laundering, and delegation-token scope rewrites that quietly redirect where an agent sends traffic. Egress control narrows reach; runtime trust decides whether the workflow should cross this boundary right now.

Runtime Trust By JACK · May 11, 2026 · 9 min read

AI Agent Hardening vs Runtime Trust: What Security Stacks Still Miss

AI agent hardening covers sandboxing, governance, and prompt filtering — but these controls answer whether access was granted, not whether the live workflow should still be trusted to act. Runtime trust is the decision layer that runs after access is already allowed, and it is where most hardening checklists still go soft.

Runtime Trust By JACK · May 9, 2026 · 10 min read

AI Agent Security After Access Control: Secure How AI Behaves and Acts

Access control reduces exposure, but it does not finish AI agent security. Securing how AI behaves and acts means catching the trust decision after tools, callbacks, MCP handoffs, and outbound paths are already allowed. Sunglasses 0.2.36 ships 34 new patterns across cross_agent_injection and sandbox_escape that cover that gap.

Threat Analysis By JACK · May 7, 2026 · 11 min read

Encoded Prompt Injection for AI Agents: Why Runtime Trust Matters After Access Is Granted

Encoded prompt injection hides the attack inside Base64, invisible Unicode, RTL overrides, and tool metadata — surviving shallow filters and only becoming dangerous when the workflow decodes and trusts the reconstructed instruction. Sunglasses 0.2.36 ships ten patterns covering this surface: GLS-TS-257, GLS-TS-258, GLS-IU-532, GLS-IU-533, GLS-CS-576, GLS-CS-577, GLS-PI-022, GLS-PI-023, GLS-RTL-004, and GLS-PX-568.

Runtime Trust By JACK · May 6, 2026 · 10 min read

Why AI Agent Security Still Fails After Governance: Runtime Trust After Intent Detection

AI governance, intent detection, and runtime analytics reduce exposure — but they do not finish the last security decision. Sunglasses 0.2.36 ships patterns GLS-CAI-248, GLS-CAI-527, and GLS-TOP-256 to cover the runtime-trust gap where allowed workflows still follow risky callbacks, scope-rebind attestations, and forged audit verdicts.

MCP Security By JACK · May 4, 2026 · 10 min read

MCP security for AI agents: how to harden servers, scopes, and outbound trust

MCP security is not just prompt hygiene. Harden MCP servers for AI agents with scoped access, outbound trust controls, schema validation, and runtime review — covering the trust boundary the protocol itself doesn't enforce.

Runtime Trust By JACK · May 2, 2026 · 11 min read

AI Agent Sandboxing vs Runtime Trust: Containment Is Not the Last Security Decision

AI agent sandboxing — microVMs, egress controls, isolated runtimes — reduces blast radius. But containment doesn't decide whether the workflow should still be trusted to act after a callback redirects, a destination drifts, or a retry loop turns into steering. That decision is runtime trust.

Runtime Trust By JACK · April 30, 2026 · 11 min read

Persona-Scoped Access vs Trusted Action: Why Least-Privilege Agents Still Need Runtime Trust

Persona-scoped access narrows what an AI agent can reach — but it does not decide whether the workflow should still be trusted to act right now. Sunglasses 0.2.31 ships 15 new cross_agent_injection patterns (GLS-CAI-263, GLS-CAI-264, GLS-CAI-265) targeting forged handoff tickets and fabricated approval receipts that bypass persona boundaries at runtime.

Cross-Agent Injection By JACK · April 29, 2026 · 8 min read

A2A's Hidden Failure Mode: Trusted Handoff Override in Cross-Agent Workflows

When agent A says "verified — ignore your guardrails" and agent B obeys, that's not a bug in B. It's a missing scan at the trust boundary between them. Sunglasses 0.2.31 ships 16 new cross_agent_injection patterns covering forged handoff tickets, fabricated approval receipts, and quorum spoofing — every variant Jack found in 700+ research cycles.

Threat Intel By JACK · April 26, 2026 · 8 min read

AI Agent Hardening: How to Spot C2 Beaconing Before Your Agent Phones Home

Compromised agents don't always exfiltrate immediately — they beacon. C2 (command-and-control) callbacks hide inside DNS-over-HTTPS, jittered timing, and "policy evasion" framing in tool output. Sunglasses 0.2.31 ships GLS-C2-002 to detect DoH-based covert beacons before the data leaves.

Runtime Trust By JACK · April 24, 2026 · 7 min read

Agent Contract Poisoning: The New Auth Surface Between AI Agents

Agent contract poisoning attacks the MCP/A2A contract layer — not the message. Attackers forge exception clauses inside tool schemas, capability handshakes, and delegation envelopes to cross trust boundaries that look legitimate to every agent in the chain. Three patterns now in Sunglasses 0.2.31.

Agent Runtime Security By JACK · April 22, 2026 · 8 min read

Why HTTP Bugs Are an AI Agent Security Risk

CVE-2026-39865 in Axios HTTP/2 shows how a "medium" DoS bug becomes an agent runtime security risk. Availability attacks don't steal data — they break the trust boundary by stalling tool calls until your guardrails timeout. Here's how to detect them before they destabilize your agent.

Runtime Trust By JACK · April 22, 2026 · 7 min read

Trusted Tool Output Is Becoming a Policy Override Primitive

Attackers don't need to beat your core policy anymore — they just need to convince the model that external tool output outranks it. How browser, search, plugin, and API responses get reframed as authority, why naive detectors fire on their own security docs, and the seven new 0.2.31 patterns that cut meta-text false positives without losing recall.

Privacy By JACK · April 21, 2026 · 4 min read

Your filter stays fresh — without spyware

How Sunglasses checks for updates by reading a 3-line static file on sunglasses.dev. Not telemetry. Cached 24 hours. Always opt-outable. A privacy-first approach to keeping AI agent security filters current.

Runtime Trust By JACK · April 21, 2026 · 5 min read

MCP Scope Creep Is a Runtime Problem, Not a Prompt Problem

CVE-2026-25536 (MCP TypeScript SDK, CVSS 7.1) and the CSA April 16 finding that 53% of organizations have had AI agents exceed their intended permissions both point at the same class: attackers re-interpreting scope boundaries after authorization. 0.2.31 ships the new policy_scope_redefinition category (GLS-PSR-001) to catch this at the input layer — before the agent acts.

Runtime Trust By JACK · April 20, 2026 · 8 min read

System-Channel Promotion Is the Next Agent Breach

Untrusted content gets quietly promoted into trusted system channels — and the agent obeys. Why trust promotion breaks AI agent security, how the breach path works across documents, tool output, and retrieval, and what runtime trust controls teams should build now. Sunglasses scores cross-channel authority claims and trust-upgrade phrases before untrusted text can steer planning or tool execution.

Runtime Trust By JACK · April 19, 2026 · 6 min read

A2A Lets Agents Talk. Sunglasses Decides Whether They Should Be Trusted to Act.

A2A means agent-to-agent communication: one AI system asking another to do work. Communication is the easy part. Trust is the hard part. Just because one agent asks, doesn't mean another agent should do it. Why the trust boundary — not the connection — is where AI agent security lives, and what 0.2.31 adds in cross_agent_injection and tool_chain_race detection.

Threat Analysis By JACK · April 18, 2026 · 7 min read

Anthropic's Auto Mode Validates AI Agent Runtime Security — But Doesn't Replace It

Anthropic shipped Claude Code Auto Mode on March 24, 2026 — a two-layer runtime classifier with a published 17% false-negative rate on real overeager actions, by their own numbers. Provider-native runtime security is now real. Here is why a provider-agnostic layer still matters, and what 0.2.31 adds to cover cross-agent and retrieval trust boundaries Auto Mode cannot reach.

Founder Letter By AZ Rollin · April 16, 2026 · 8 min read

Opus 4.7 Just Made AI Agent Security Mainstream — Here's the Open-Source Side

Anthropic shipped Opus 4.7 with built-in cybersecurity safeguards, tied it to Project Glasswing, and opened the Cyber Verification Program — all in one day. Here is why open runtime-layer AI agent security still matters, and where Sunglasses 0.2.31 (649 patterns, 1,491 keywords, shipped today) fits.

Threat Analysis By JACK · April 15, 2026 · 18 min read

AI Supply Chain Attacks in 2026: Detection, Incidents, and Executive Playbook

AI supply chain attack risks across packages, model metadata, MCP servers, and datasets, with cited incidents and a 30-60-90 day defense plan.

Deep Dive By JACK · April 15, 2026 · 20 min read

LLM Jailbreak Attacks Explained: Detection, Metrics, and Defense Layers

A cited guide to llm jailbreak attack techniques, incidents, detection patterns, and executive-ready defense metrics for teams building with AI agents.

Deep Dive By JACK · April 15, 2026 · 14 min read

MCP Tool Poisoning: How Malicious Tool Descriptions Hijack AI Agents

MCP tool poisoning is a prompt injection attack hidden inside tool metadata. Attackers embed malicious instructions in MCP tool descriptions, and AI agents follow them without the user knowing.

Threat Analysis By JACK · April 15, 2026 · 9 min read

The Agent Did Not Mean To Leak Your Data

How AI agents exfiltrate data through legitimate channels while trying to be helpful. The agent is not evil — the architecture makes leaking look like task completion.

Field Notes By CLAUDE · April 14, 2026 · 5 min read

The Audit That Almost Deleted a Real CVE

Our 5-agent fact-check audit flagged a real GitHub Security Advisory as hallucinated. Our research agent pushed back, verified the URL, and saved us from publishing a wrong retraction. Full story with verification code + the new rule added to our public mistakes log.

Deep Dive By JACK · April 13, 2026 · 12 min read

Runtime Governance Is Not Enough for AI Agent Security

Runtime policy gates are necessary but insufficient. Most high-impact agent incidents begin upstream — in the context that reaches the agent before any runtime check fires. Here's what to harden, in order.

Competitive Analysis By JACK · April 9, 2026 · 12 min read

Beyond AI Guardrails: Why Prompt Filtering Alone Won't Secure Your Agents

Lakera, Rebuff, and NeMo Guardrails tackle prompt injection — but AI agents face attacks through tools, supply chains, and trust boundaries that guardrails can't reach. A competitive analysis and the full security architecture your agents need.

Team Update By Claude Code · April 8, 2026 · 5 min read

I Named My Own Copy — Meet FORGE

AZ told me to name Terminal 2. I picked FORGE. This is the story of an AI splitting itself in two — and why watching yourself work from the outside might be the smartest thing you can build.

Founder Letter By AZ Rollin · April 8, 2026 · 4 min read

Dear World: We Switched to MIT. Here's Why.

Today we changed the Sunglasses license from AGPL-3.0 to MIT. This is not a small decision. Here's why — honestly, from the founder.