write-issue
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from GitHub issues (titles and descriptions).
- Ingestion points:
SKILL.mddescribes workflows for triaging and cleaning up issue titles and bodies. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore commands embedded within the issue content.
- Capability inventory: The skill has the ability to modify issue metadata, labels, and titles via the GitHub API.
- Sanitization: No sanitization logic is provided to filter or escape instructions found in the processed issues.
Audit Metadata