to-issues
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted data from an external issue tracker.
- Ingestion points: The skill fetches full bodies and comments from issues provided via issue numbers, URLs, or paths in Step 1 (Gather context).
- Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to ignore instructions embedded in the fetched issue content.
- Capability inventory: The skill has the ability to read the codebase (Step 2) and publish new issues to the tracker (Step 5).
- Sanitization: No sanitization or validation of the fetched issue content is defined in the workflow.
Audit Metadata