rollback
Warn
Audited by Snyk on Jul 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The workflow includes an “External Research (librarian agent)” track intended to fetch “rollback patterns for similar changes,” which at runtime is likely to involve public web content or other outsider-authored sources being ingested into the LLM context via that agent, creating indirect prompt-injection exposure.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata