jt-open-work
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Git branches, which could theoretically contain instructions intended to influence the agent's behavior during the review process.
- Ingestion points: Content is read from branches
สาขาคิวandcard-<id>as described inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided in the skill instructions.
- Capability inventory: The agent uses tools to read Git branch names, file content (cards, plans), and diffs.
- Sanitization: No sanitization or validation of the branch content is mentioned before presenting it to the user.
Audit Metadata