tek-mark-close
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to be used as a 'reason' for closing a card.
- Ingestion points: User input provided via the
/tek-mark-closecommand (SKILL.md). - Boundary markers: None explicitly defined to separate the 'reason' string from the rest of the prompt logic.
- Capability inventory: Git checkout, file modification of
card-loop/board.md, Git commit, and closing Merge Requests (SKILL.md). - Sanitization: None described; the text is appended directly to the markdown file.
- Assessment: While user input is interpolated into file content and commit messages, the operations are constrained to a specific local file and Git workflow. This is a common pattern for automation tools and does not present a significant security risk.
Audit Metadata