lookup
Warn
Audited by Snyk on Jul 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). This skill’s required runtime workflow takes outsider-authored user text as the
queryarguments toctx7 libraryand thenctx7 docs/mcp__context7__query-docs, meaning the LLM ingests free-form user prompts before fetching Context7 content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill calls Context7 at runtime to retrieve docs that are injected into the agent's context (CLI default base URL https://context7.com and the MCP endpoint https://mcp.context7.com/mcp), so these endpoints directly supply content that will influence prompts/results.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata