executing-plans

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses a defensive workflow that requires agents to pause for feedback and critically evaluate inputs, mitigating potential misuse.\n- [PROMPT_INJECTION]: The skill facilitates the processing of external implementation plans, which represents an indirect prompt injection surface.\n
  • Ingestion points: Reads external plan files as instructed in Step 1 of SKILL.md.\n
  • Boundary markers: No explicit data delimiters are defined for the plan files.\n
  • Capability inventory: Generic task execution and verification within the agent's environment.\n
  • Sanitization: The instructions mandate a 'critical review' and 'raised concerns' with a human partner before execution, providing a procedural layer of safety.\n- [NO_CODE]: The skill is entirely instruction-based and does not include scripts, binaries, or automated installers that would increase the technical attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:36 AM
Security Audit — agent-trust-hub — executing-plans