continue-pr
Warn
Audited by Snyk on Jul 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). This workflow instructs the agent to fetch and read the PR body and review comments at runtime (outsider-authored free text from other contributors) via the PR-fetch step in item 2, which then gets included in the LLM context for tasking.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata