executing-plans
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides procedural guidance for software development tasks and does not contain any malicious patterns or unauthorized access attempts.
- [PROMPT_INJECTION]: The skill processes external plan files which could serve as a surface for indirect prompt injection.
- Ingestion points: SKILL.md Step 1 requires the agent to read an external plan file.
- Boundary markers: No explicit delimiters or warnings to disregard instructions within the plan are present.
- Capability inventory: The agent is instructed to execute tasks that involve file system modifications and running verification commands.
- Sanitization: The skill includes robust mitigations requiring the agent to critically review plans, identify concerns, and stop immediately if instructions are ambiguous or blockers are hit.
Audit Metadata