executing-plans
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to load and execute instructions from a "plan file" provided by the user or an external process.
- Ingestion points: SKILL.md, Step 1 ("Read plan file").
- Boundary markers: The skill lacks explicit boundary markers or instructions to ignore nested directives within the plan file, though it does include a "Review critically" step.
- Capability inventory: The skill enables full task execution, including shell commands and editor operations, based on the steps defined in the plan.
- Sanitization: No sanitization or schema validation is applied to the plan content before execution.
- [COMMAND_EXECUTION]: The workflow facilitates the execution of arbitrary tasks and verification steps.
- Evidence: Step 2 instructs the agent to "Follow each step exactly" and "Run verifications as specified," which implies the use of shell tools and editor commands to fulfill instructions found in external data.
Audit Metadata