skills/jonaskahn/specwright/sw-plan/Gen Agent Trust Hub

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.py to validate task coverage and ensure alignment with the project's acceptance criteria. The script imports from a local kitlib library to manage workspace operations and frontmatter parsing.
  • [PROMPT_INJECTION]: The SKILL.md contains 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
Risk Level
SAFE
Analyzed
Nov 11, 2026, 08:30 AM