work-loop
Warn
Audited by Snyk on Jul 30, 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
work-loopskill ingests outsider-authored free text from GitHub issues/PRs at runtime by sweeping and evaluating frontier items’ titles/bodies/comments and linked-PR text/diffs during its cycle (intake sweep via/work-items:triage, admission gate classification, and execution), so a user can post poison into those tracker backlogs for the workflow to read.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata