react-component-documentation

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
  • Ingestion points: The agent is instructed to read component source files (.tsx) and existing documentation (.mdx) to extract information for the generated output.
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the data read from source files.
  • Capability inventory: The skill uses Write and Edit tools to modify or create files in the local filesystem.
  • Sanitization: There is no evidence of sanitization or filtering of content (such as code comments or string literals) before it is interpolated into the generated documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 10:27 PM