growth-experiment

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files and user input to generate documentation, creating a potential surface for indirect instructions if source files are compromised.\n
  • Ingestion points: The skill reads from knowledge/kpis.md, knowledge/icp/personas.md, and knowledge/learnings.md.\n
  • Boundary markers: No explicit delimiters or instructions to disregard embedded commands were found in the workflow.\n
  • Capability inventory: The skill is configured to write files to the output/growth-experiment/ directory.\n
  • Sanitization: No evidence of input validation, escaping, or filtering was found for the data read from external knowledge files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:28 AM
Security Audit — agent-trust-hub — growth-experiment