executing-plans
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and execute instructions from a "plan file" which may originate from an untrusted source or be influenced by external data.
- Ingestion points: The skill reads an external plan file in Step 1 of the implementation process.
- Boundary markers: The instructions do not define specific delimiters for the plan content, though they recommend a critical review phase before execution.
- Capability inventory: The skill allows the agent to modify code, run tests, and execute git commands based on the plan's content.
- Sanitization: No automated sanitization is specified; the skill relies on the agent's critical review and the user's feedback during batch checkpoints to mitigate risks.
Audit Metadata