api-documentation-generator

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content (comments and strings) within a user's codebase.
  • Ingestion points: Analyzes codebase files and metadata to extract API endpoint information.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or warnings for the agent to ignore instructions found within the code being analyzed.
  • Capability inventory: Requires file system read access to perform analysis and file system write access to generate documentation files; no network exfiltration or command execution logic is present.
  • Sanitization: Absent; the instructions do not define any validation or filtering of input data extracted from the code.
  • [NO_CODE]: This skill consists entirely of markdown instructions and documentation examples without any associated scripts, binaries, or complex configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 06:10 PM
Security Audit — agent-trust-hub — api-documentation-generator