context7-efficient

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches public library documentation through Context7 MCP (see SKILL.md and scripts/fetch-raw.sh → scripts/mcp-client.py called by scripts/fetch-docs.sh), processes that third‑party documentation, and returns it into the LLM workflow—thereby exposing the agent to untrusted public web content that could carry indirect prompt-injection instructions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill repeatedly runs and depends on a remote npm package at runtime via the command "npx -y @upstash/context7-mcp" (used in scripts like fetch-raw.sh and fetch-docs.sh), which fetches and executes remote code and provides MCP responses that directly control the documentation/prompts injected into the LLM context.