mcp-development

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: 0.90). The skill explicitly fetches and ingests arbitrary URLs as part of its workflow (see SKILL.md "Prompts" -> prompts/get which calls fetchDocument(args.url) to build messages, and Resources/read which returns resource contents for given URIs), so untrusted public web content could be read and materially influence agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). The skill includes a runtime fetch of an externally-provided URL (fetchDocument(args.url) in references/mcp-patterns.md's prompts/get handler) that is required and its contents are injected directly into the prompt, so an external URL supplied at runtime can control agent instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 07:20 AM