github-issue-solve
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external issue content. Ingestion points: GitHub issue bodies and comments via
ghcommands (SKILL.md and references/issue-solve-workflow.md). Boundary markers: Absent. Capability inventory: GitHub CLI usage, file system operations, and shell command execution for verification. Sanitization: Absent. This surface is intrinsic to the skill's function and does not indicate malicious intent. - [COMMAND_EXECUTION]: Executes
ghCLI commands and project-specific verification commands during the implementation phase to validate code changes. - [DATA_EXFILTRATION]: Performs network-based operations to interact with GitHub official APIs for issue retrieval and pull request submission.
Audit Metadata