updating-lockstep
Warn
Audited by Snyk on May 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and inspects upstream git repositories and their tags (Phase 3: "git fetch origin --tags", checkout of "$LATEST") and consumes the drift report from
pnpm run lockstep --json(Phase 2), which are untrusted third-party repo contents that the agent reads and uses to decide checkouts/bumps and commit actions, so external repo data can materially influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata