review
Warn
Audited by Snyk on Jul 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The workflow fetches outsider-authored issue/PR text via
docs/agents/issue-tracker.md(step 2.1) and then includes the fetched spec contents in the Spec sub-agent prompt, so the LLM ingests free-form text authored by external parties at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata