collage-layout-expert
Warn
Audited by Snyk on Mar 5, 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 SKILL.md explicitly lists an MCP integration "WebFetch — Fetch documentation, tutorials, design references", which directs the agent to fetch and consume open/public third-party content (documentation/tutorials/design references) as part of its workflow and thus could materially influence decisions and tool use.
Audit Metadata