coding-agent
Warn
Audited by Snyk on Oct 8, 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 workflow includes reading and reviewing GitHub pull requests (e.g.,
gh pr checkoutorgit diff origin/main...origin/pr/XX), which exposes the agent to outsider-authored free text in PR descriptions, comments, and diffs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata