skills/ianphil/my-skills/prime/Gen Agent Trust Hub

prime

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: Executes the git ls-files command to map the project's file structure. This is a standard operation for codebase orientation.
  • [PROMPT_INJECTION]: Potential surface for indirect prompt injection as the skill reads and processes the content of README.md and .ainotes/memory.md. Malicious instructions embedded in these files could attempt to influence the agent's behavior.
  • Ingestion points: Reads project files README.md and .ainotes/memory.md (SKILL.md).
  • Boundary markers: Not specified in the skill instructions.
  • Capability inventory: Reading local files and executing shell commands (git).
  • Sanitization: No explicit sanitization of file content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 03:29 AM