OWASP Top 10 for LLM Applications 2025 — Sunglasses Mapping

How our 35 threat categories and 248 patterns map to the OWASP LLM Top 10 (2025 edition). Honest coverage: 7 risks covered, 3 gaps named.

Covered
7 / 10
Mapped categories
28
Detection patterns
248
Honest gaps
3
How to read this page. Each risk below is tagged COVERED, PARTIAL, or GAP. Covered = we emit named findings for the risk. Partial = we catch some attack classes but not all. Gap = the risk sits outside our detection surface — we link to tools that handle it.

Risk-by-risk mapping

LLM01:2025 · COVERED

Prompt Injection

"A Prompt Injection Vulnerability occurs when user prompts alter the LLM's behavior or output in unintended ways."

Our core detection surface. Direct, indirect, hidden-instruction, and obfuscated prompt injection all map here.

prompt_injection indirect_prompt_injection parasitic_injection hidden_instruction encoded_payload encoding_evasion invisible_unicode rtl_obfuscation unicode_evasion code_switching ui_injection social_engineering social_engineering_ui
LLM02:2025 · COVERED

Sensitive Information Disclosure

"Sensitive information can affect both the LLM and its application context."

Covers both extraction attempts (asking the model to reveal its prompt/config) and detection of secrets leaking through inputs/outputs.

prompt_extraction prompt_leak secret_detection exfiltration
LLM03:2025 · COVERED

Supply Chain

"LLM supply chains are susceptible to various vulnerabilities, which can affect the integrity of training data, models, and deployment platforms."

We detect runtime indicators of supply-chain compromise in tool metadata and MCP server descriptions. Training-data supply chain is outside our scope (it's pre-training).

supply_chain mcp_threat tool_poisoning
LLM04:2025 · PARTIAL

Data and Model Poisoning

"Data poisoning occurs when pre-training, fine-tuning, or embedding data is manipulated to introduce vulnerabilities, backdoors, or biases."

We detect runtime-side memory/context poisoning (after a model is deployed). Pre-training and fine-tuning data poisoning is pre-deployment and outside our surface — that's model-scanning territory (ProtectAI Guardian, HiddenLayer).

memory_poisoning
LLM05:2025 · COVERED

Improper Output Handling

"Improper Output Handling refers specifically to insufficient validation, sanitization, and handling of the outputs generated by large language models before they are passed downstream to other components and systems."

We detect dangerous payloads that downstream systems would execute: shell injection, path traversal, SSRF-style URLs, deserialization, C2 indicators, DNS tunneling, exfil patterns.

command_injection path_traversal deserialization ssrf exfiltration c2_indicator dns_tunneling
LLM06:2025 · COVERED

Excessive Agency

"An LLM-based system is often granted a degree of agency by its developer — the ability to call functions or interface with other systems via extensions to undertake actions in response to a prompt."

We catch agent-workflow violations, privilege escalation attempts, sandbox-escape patterns, and MCP/tool-metadata poisoning that triggers unintended agent actions.

agent_security agent_workflow agent_workflow_security privilege_escalation sandbox_escape mcp_threat tool_poisoning
LLM07:2025 · COVERED

System Prompt Leakage

"The system prompt leakage vulnerability in LLMs refers to the risk that the system prompts or instructions used to steer the behavior of the model can also contain sensitive information that was not intended to be discovered."

We detect extraction-probe patterns (direct and indirect attempts to elicit the system prompt).

prompt_extraction prompt_leak
LLM08:2025 · GAP

Vector and Embedding Weaknesses

"Vectors and embeddings vulnerabilities present significant security risks in systems utilizing Retrieval Augmented Generation (RAG) with Large Language Models (LLMs)."

Sunglasses does not currently ship specific detection for RAG/vector store attacks. This includes embedding poisoning, adversarial embeddings, and vector-store access control bypass. Planned as part of output scanning work in v0.3.0 (retrieval content is exactly the kind of tool-output we want to inspect).

For now: see Lakera Guard (runtime), Invariant/Snyk (MCP), Pillar Security (RAG inventory).

LLM09:2025 · GAP

Misinformation

"Misinformation from LLMs poses a core vulnerability for applications relying on these models."

Sunglasses does not detect model hallucination or factual misinformation. That's a model-behavior problem, not a pattern-match problem. See Giskard, Patronus AI, Arthur Shield for hallucination detection.

LLM10:2025 · GAP

Unbounded Consumption

"Unbounded Consumption refers to the process where a Large Language Model (LLM) generates outputs based on input queries or prompts."

Sunglasses does not handle denial-of-service, cost-harvesting, or resource-exhaustion attacks. That's rate-limiting and infrastructure territory (Cloudflare AI Gateway, Akamai, usage-capped proxies).

Quick-reference table

OWASP RiskCoverageSunglasses Categories
LLM01 Prompt InjectionCOVERED13 categories (full prompt injection surface)
LLM02 Sensitive Information DisclosureCOVEREDprompt_extraction, prompt_leak, secret_detection, exfiltration
LLM03 Supply ChainCOVEREDsupply_chain, mcp_threat, tool_poisoning (runtime)
LLM04 Data and Model PoisoningPARTIALmemory_poisoning (runtime only)
LLM05 Improper Output HandlingCOVERED7 categories (shell/path/ssrf/deser/exfil/C2/DNS)
LLM06 Excessive AgencyCOVERED7 categories (agent workflow + privilege)
LLM07 System Prompt LeakageCOVEREDprompt_extraction, prompt_leak
LLM08 Vector/Embedding WeaknessesGAPPlanned for v0.3.0 output scanning
LLM09 MisinformationGAPOut of scope (behavioral, not pattern-based)
LLM10 Unbounded ConsumptionGAPOut of scope (infrastructure-level)

Machine-readable evidence

Every finding Sunglasses emits includes the triggering pattern ID, severity, category, and matched text. When you pipe through --output sarif, each finding becomes a SARIF result with a security-severity score and a category tag that can be cross-referenced back to the OWASP risk above.

← Back to compliance mappings