ln-002-best-practices-researcher

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it ingests external, potentially untrusted data to generate documentation.
  • Ingestion points: The story_context parameter in SKILL.md is used to provide context for research and document generation.
  • Boundary markers: There are no defined delimiters or instructions to the agent to disregard embedded instructions within the story_context input.
  • Capability inventory: The skill has the capability to perform web searches and write files to the local file system (e.g., docs/guides/, docs/adrs/).
  • Sanitization: The skill does not implement sanitization or validation of the story_context before interpolating it into documentation templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 11:55 PM