software-design
Warn
Audited by Snyk on Jul 4, 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). The workflow reads “All open issues in the epic, with comments and labels” (step 1) and later rewrites those issue bodies (step 8), so any outsider-authored issue/comment text from the tracker is ingested into the agent’s LLM context via the issue-tracker API.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata