gitlab-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for Issues and Merge Requests which are surfaces where data from external contributors enters the agent context. 1. Ingestion points: Issue and MR templates in SKILL.md. 2. Boundary markers: None present in templates. 3. Capability inventory: None (informational skill). 4. Sanitization: None demonstrated.
- [SAFE]: The skill utilizes official GitLab security templates in CI/CD examples which are trusted resources.
Audit Metadata