and-pack
Warn
Audited by Snyk on Jul 21, 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). SKILL.md’s required runtime “Process 1. Load source of truth” explicitly instructs the agent to read “the work body, comments or receipts… and attachments,” which are commonly outsider-authored free text (e.g., issue/PR comments or linked receipts) and then feed that content into the agent context for packaging.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata