claude-code-cicd
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's GitHub/GitLab CI workflows and SDK examples explicitly read and feed user-generated content—e.g., GitHub issue titles/bodies, PR/merge request diffs and changed files (via github.event.* and git diff)—directly into Claude for analysis, exposing the agent to untrusted third-party input that could enable indirect prompt injection.
Audit Metadata