visionera
Warn
Audited by Snyk on Apr 28, 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.md Step 2 ("Research the domain") explicitly requires performing "3-5 targeted searches" and to survey "communities, forums, common frustrations" (public web/social sources), which the agent is expected to read and synthesize into the project's vision, allowing untrusted third-party content to influence decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata