presubmit-checks
Warn
Audited by Snyk on May 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's required workflow explicitly runs a "check-refs" subagent to "verify all cited papers exist in academic databases" (see "Checks" and "Workflow" -> "Agent 1: Run check-refs (bibsleuth existence check)"), which entails fetching open/public third-party bibliographic content that is used to mark unverified/retracted citations and thus can change blocker/warning decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata