gitlab-code-review
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from GitLab merge requests which could contain malicious instructions.
- Ingestion points: The skill retrieves and processes untrusted data including merge request titles, descriptions, and code diffs (SKILL.md).
- Boundary markers: The prompt instructions lack explicit delimiters or specific instructions to ignore instructions embedded within the merge request data.
- Capability inventory: The skill has permissions to read arbitrary repository files and post notes or discussion threads to the GitLab instance (SKILL.md).
- Sanitization: There is no evidence of sanitization or validation of the content fetched from the GitLab server before it is incorporated into the agent's context.
Audit Metadata