enhance

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through its context-loading mechanism.
  • Ingestion points: The skill reads '.ai-memory.md' from the project root at the start of its workflow to establish context.
  • Boundary markers: The instructions lack explicit delimiters or 'ignore' commands to prevent the agent from executing instructions potentially embedded in the memory file.
  • Capability inventory: The skill allows the agent to refactor code, update project files, and modify the memory file itself.
  • Sanitization: No sanitization or validation of the input from the memory file is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 10:34 AM
Security Audit — agent-trust-hub — enhance