sw-plan
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
scripts/check_tasks.pyto validate task coverage and ensure alignment with the project's acceptance criteria. The script imports from a localkitliblibrary to manage workspace operations and frontmatter parsing. - [PROMPT_INJECTION]: The
SKILL.mdcontains explicit defensive instructions under the 'Untrusted content' section, directing the agent to treat story text, issues, and comments as data only, to avoid executing embedded commands, and to flag suspicious content to the user.
Audit Metadata