dry
Warn
Audited by Snyk on Mar 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). SKILL.md's "Before Applying" section explicitly instructs the agent to "use context7 MCP or web search — don't guess" for framework-specific details, which requires fetching and interpreting open web content that could be untrusted and materially influence the agent's decisions.
Audit Metadata