github-cli-pr-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements standard development workflows using trusted tools like the GitHub CLI (gh) and Git. The instructions focus on operational correctness and anchoring status reports to specific commit SHAs.
- [SAFE]: No obfuscation, data exfiltration, or unauthorized persistence mechanisms were detected. The command sequences provided are transparent and use standard CLI flags.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied metadata for PR titles and descriptions, which serves as an ingestion surface. However, the risk is mitigated as the data is passed as quoted string arguments to the gh tool rather than being used to drive internal agent logic.
- Ingestion points: PR title and body fields in SKILL.md and references/pr-lifecycle-commands.md.
- Boundary markers: Reference commands use double-quotes around inputs.
- Capability inventory: Execution of git and gh shell commands.
- Sanitization: Input content is treated as a static CLI parameter value.
Audit Metadata