document

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing data from external project sources to update documentation.
  • Ingestion points: The skill reads AGENTS.md, TASKS.md, task documents, test reports, and file changes via git diff (SKILL.md).
  • Boundary markers: No delimiters or safety instructions are present to prevent the agent from following instructions embedded in these documents.
  • Capability inventory: The skill uses git diff (subprocess) and performs file-write operations to the docs/ directory, LEARNINGS.md, AGENTS.md, and TASKS.md (SKILL.md).
  • Sanitization: No sanitization or content validation is performed on the ingested data before it is written to the project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 10:46 AM
Security Audit — agent-trust-hub — document