opportunity-scan
Warn
Audited by Snyk on Aug 12, 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 runtime workflow ingests an outsider-chosen target RUN or a WINDOW OF LOGS from user-provided artifacts/logs (“A RUN: read the artifacts in full” / “pull out what you actually did… logs… so only frequencies and representative samples enter your context”), and those artifacts can include free text authored by outsiders (e.g., PR/review bodies, session transcripts, issue content embedded in the run artifacts).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata