cut
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from parent tickets and specifications to generate sub-issues and commit messages.
- Ingestion points: The skill reads parent tickets and specification files (e.g.,
spec/<capability>) as outlined in Step 1 ofSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or explicit 'ignore' instructions when the agent processes these external files.
- Capability inventory: Across its workflow, the skill possesses capabilities to read files, create sub-issues in a tracker (Step 5), and perform git commit and push operations (Step 6).
- Sanitization: There is no evidence of explicit sanitization or validation of the content read from external documentation before it is used to influence the generation of new issues or commit descriptions.
Audit Metadata