git-pr-workflows-git-workflow
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external code changes and test results. This risk is inherent to its primary purpose as a code review tool. * Ingestion points: External repository content and file summaries are ingested in sub-skills/1-code-quality-assessment.md and sub-skills/1-change-analysis-and-categorization.md. * Boundary markers: Data is interpolated into subagent prompts using placeholders without explicit boundary delimiters. * Capability inventory: Includes execution of test suites via the test-automator agent and repository manipulation via the deployment-engineer agent. * Sanitization: No specific content filtering or sanitization is mentioned in the instructions.
- [SAFE]: No evidence of malicious intent, data exfiltration, or unauthorized command execution was found. The skill adheres to development best practices such as Conventional Commits and includes proactive security checks.
Audit Metadata