paint-with-code
Warn
Audited by Snyk on Nov 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow has the agent find public-domain or licensed reference pictures and record "each page link and licence," which means actively searching and fetching arbitrary web pages that outsiders can author, so the risk is low rather than medium.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill instructs installing and running code from github.com/codepawl/paintkit, an individual/community-owned repository (not a recognized vendor or foundation), via pip/uv, which is a Git-style locator that is actually used; this is common but unofficial provenance, so medium.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata