openpencil-design
Warn
Audited by Snyk on Apr 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly includes fetching and ingesting arbitrary external media via image src/image fill URLs and search-generated images (e.g., the "image" src examples, "imageSearchQuery"/AI image placeholders, and the DSL
G(parent, "search", "query")), which are untrusted third-party sources and would be read/used by the agent during design/refine operations and thus could indirectly inject instructions or alter behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata