pr
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (LOW): The skill utilizes local shell commands (
git,gh) to inspect repository state, view branches, and push changes. These operations are required for the skill's primary purpose. - DATA_EXFILTRATION (SAFE): While the skill reads repository data via
git diff, it implements a comprehensive exclusion list for sensitive file types (e.g.,.pem,.key,.crt,.p12) to prevent credentials from being included in the AI's context. - PROMPT_INJECTION (LOW):
- Ingestion points: The skill ingests untrusted data from
git logandgit diffinSKILL.md. - Boundary markers: Absent. The skill does not use specific delimiters or warnings to ignore instructions within the ingested code or commit messages.
- Capability inventory: The skill can perform write actions including
git pushandgh pr create. - Sanitization: The skill includes a 'Single confirmation' step (Step 4) that requires the user to approve the PR title, description, and the push/create actions before execution, which serves as a human-in-the-loop safeguard.
Audit Metadata