skills/upstash/context7/context7-docs/Gen Agent Trust Hub

context7-docs

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [DATA_EXFILTRATION]: The skill makes network requests to context7.com to fetch documentation and code examples. It uses the CONTEXT7_API_KEY environment variable for authentication and advises users against passing sensitive credentials or proprietary code in search queries, adhering to security best practices.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface.
  • Ingestion points: Untrusted content is brought into the agent context from the Context7 API via the resolve-library-id and query-docs tools.
  • Boundary markers: The skill does not define specific delimiters or isolation instructions to prevent the model from following potentially malicious instructions embedded in the retrieved documentation.
  • Capability inventory: The skill's capabilities are limited to information retrieval; it does not request or possess permissions for arbitrary command execution or sensitive local file access.
  • Sanitization: No explicit sanitization or filtering of the retrieved documentation or code snippets is described in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 12:52 PM
Security Audit — agent-trust-hub — context7-docs