working-with-notebooks
Warn
Audited by Snyk on Sep 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill instructs the agent to read GitHub workflow/job logs using
gh run viewandgh pr checks, which can contain untrusted outsider-authored content from PR comments, commit messages, or failing test outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata