fetch-issues
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from an external issue tracker, which constitutes a surface for indirect prompt injection where instructions could be embedded in issue titles or summaries.
- Ingestion points: Fetches issue content based on the tracker resolved in
references/issue-tracker.md. - Boundary markers: No delimiters or "ignore instructions" markers are used for the external content.
- Capability inventory: The skill is restricted to listing and printing issue rows; it does not include file writing or code execution capabilities.
- Sanitization: No sanitization, validation, or escaping of the fetched issue strings is performed before they are printed to the output.
Audit Metadata