create-a-plan
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and follows a standard workflow for gathering technical requirements from a user to generate a project plan.
- [COMMAND_EXECUTION]: While the skill mentions the user will provide a path to a spec or plan file, it does not include any arbitrary shell execution or dangerous commands within its own instructions.
- [DATA_EXFILTRATION]: There are no network requests or external data transfers. Output is written locally to
PLAN.md. - [PROMPT_INJECTION]: The skill contains no instructions attempting to bypass model safety filters or override system behavior in a malicious way.
- [INDIRECT_PROMPT_INJECTION]: Although the skill processes user-provided specs (Phase 0), it is a static analysis tool that produces a document for human review, and its capabilities are limited to text processing and local file writing.
Audit Metadata