executing-plans
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill promotes safe development practices, including human-in-the-loop checkpoints and branch protection rules.
- [PROMPT_INJECTION]: The skill processes external implementation plans which represent a surface for indirect prompt injection. 1. Ingestion points: External plan files are read in Step 1. 2. Boundary markers: No specific delimiters are used to isolate plan content. 3. Capability inventory: The agent can execute commands and modify files during task execution. 4. Sanitization: No sanitization is performed on plan content.
- [COMMAND_EXECUTION]: The skill requires the agent to execute steps and verifications defined in the plan, which is the intended function of the tool.
Audit Metadata