resolve-backport-conflicts
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes content from external pull requests. This is inherent to the functional purpose of the skill.
- Ingestion points: Untrusted data is retrieved using
gh pr viewandgh pr diffinSKILL.md. - Boundary markers: The instructions do not define markers to separate untrusted PR data from the agent's instructions.
- Capability inventory: The skill utilizes
git commit,git push, andgh pr editto update the repository and PR state. - Sanitization: Content from pull requests is not sanitized before being interpreted by the agent.
Audit Metadata