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 detect runs scripts/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 only scripts/ carve-out), and outputs violations—so an outsider can post poison by editing those files/creating content that the workflow scans.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 30, 2026, 07:54 PM
Issues
1
Security Audit — snyk — audit-encapsulation