audit-encapsulation
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 runtime workflow for
audit-encapsulation detectrunsscripts/detect.sh, which reads outsider-authored free text from the consumer repo’s in-scope authoring surfaces (e.g.,README.md,.github/workflows,docs/,.claude/*), greps for citations into other skills’ private directories (excluding onlyscripts/carve-out), and outputs violations—so an outsider can post poison by editing those files/creating content that the workflow scans.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata