qa-github-issues-enhanced
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external sources including bug reports, coverage gap reports, and bulk CSV/JSON data. This data is interpolated into GitHub issue templates and created as issues via the GitHub MCP.
- Ingestion points: Ingestion occurs at the start of the workflow in SKILL.md, taking data from qa-coverage-analyzer, qa-spec-auditor, qa-flaky-detector, and user-provided bulk files.
- Boundary markers: The instructions do not specify the use of delimiters or warnings for the agent to ignore instructions embedded within the processed data.
- Capability inventory: The skill uses GitHub MCP tools to perform network operations, including creating and updating issues, labels, and milestones in GitHub repositories.
- Sanitization: There is no mention of sanitizing or validating the content of the external inputs before they are used to populate issue fields.
Audit Metadata