mcp-context7
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill ingests untrusted external data from a documentation service via the Context7 MCP server, creating an attack surface for indirect prompt injection.\n
- Ingestion points: Document snippets retrieved by the @upstash/context7-mcp tool.\n
- Boundary markers: None specified in prompt templates to delimit external content.\n
- Capability inventory: No executable scripts, subprocess calls, or file-write operations are present in the skill files.\n
- Sanitization: No evidence of sanitization or validation for the retrieved documentation strings.\n- No Code (SAFE): The skill consists exclusively of instructional Markdown and text files; no executable scripts, binaries, or active configuration files are included in the package.
Audit Metadata