skills/mattpocock/skills/implement/Gen Agent Trust Hub

implement

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external PRD and issue documentation which introduces a surface for indirect prompt injection. A malicious set of instructions in the documentation could attempt to deviate the agent from its intended implementation path.
  • Ingestion points: PRDs and issue descriptions processed during the implementation phase.
  • Boundary markers: None defined within the SKILL.md instructions.
  • Capability inventory: Shell execution of testing frameworks and typecheckers, along with git commit operations.
  • Sanitization: No sanitization or verification of the external input content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 02:22 PM
Security Audit — agent-trust-hub — implement