api-documentation

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Vulnerability Surface.
  • Ingestion points: The skill is designed to process external artifacts including OpenAPI/GraphQL schemas, code annotations, and test fixtures as primary sources of truth (documented in SKILL.md under Step 3).
  • Boundary markers: The instructions lack explicit requirements for the agent to use delimiters or security-focused boundary markers when interpolating content from these external sources into its prompts.
  • Capability inventory: The skill's environment grants the agent significant file system capabilities via Read, Write, Edit, Glob, and Grep tools, which could be abused if an ingested specification contains malicious instructions.
  • Sanitization: There are no instructions for validating, filtering, or sanitizing the content of the ingested specifications before the agent processes them.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 01:51 PM
Security Audit — agent-trust-hub — api-documentation