mcp-context7-docs

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). Yes — the skill instructs piping a raw GitHub install.sh from an unfamiliar account (raw.githubusercontent.com/vaayne/…) directly to sh and uses an unverified service endpoint (mcp.context7.com) to run downloaded CLI tools, which is a high-risk pattern for distributing malware.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow requires calling the external Context7 MCP service (https://mcp.context7.com/mcp) via the queryDocs tool to retrieve "up-to-date documentation and code examples for any programming library or framework," meaning the agent ingests and acts on externally sourced public/third‑party documentation and examples that could contain user-generated or untrusted instructions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill calls the MCP endpoint (https://mcp.context7.com/mcp) at runtime via mh invoke to fetch documentation/code examples which are injected into the agent's context and thus can directly control prompts.