ui-agent-patterns
Fail
Audited by Snyk on Jul 9, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.70). The TomeVault links point to an unfamiliar third‑party distribution site that advertises installing a "Relay" (likely an installer) and could be used to deliver executables, while the GitHub repo links are standard source-repository pages and not directly suspicious.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The required workflow described in SKILL.md includes “search_web”/“read_figma” permissions and web research steps, which at runtime can fetch public web content and inject that outsider-authored free text into the agent’s prompt/context.
Issues (2)
E005
CRITICALSuspicious download URL detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata