fern-docs
Warn
Audited by Snyk on Jul 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). SKILL.md instructs using Fern’s live docs via an MCP server (public web content fetched at runtime), which can return arbitrary markdown text that the agent may ingest into the LLM context.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill explicitly instructs the agent to connect to and fetch content from Fern's live MCP server (https://buildwithfern.com/learn/_mcp/server) and to fetch multiple Fern docs URLs (e.g. https://buildwithfern.com/learn/docs/getting-started/overview.md, https://buildwithfern.com/learn/llms.txt, and several others) at runtime to drive behavior, so these remote resources can directly influence agent prompts and actions.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata