triage
Warn
Audited by Snyk on Jul 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). At runtime, the workflow’s “Gather context” step reads the full body/comments/labels of issues and external PRs from the issue tracker (outsider-authored text), which is then ingested into the agent’s LLM context for triage and brief generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata