mcp-context7

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [No Code] (SAFE): The skill consists entirely of markdown instructions and metadata. It does not include any scripts, binaries, or configuration files that execute logic on the host system.
  • [Indirect Prompt Injection] (LOW): The skill fetches content from an external documentation provider (@upstash/context7-mcp), creating a surface for indirect prompt injection if the source documentation were compromised.
  • Ingestion points: Documentation snippets retrieved via the context7 MCP server.
  • Boundary markers: Absent in prompt templates.
  • Capability inventory: Limited to documentation retrieval and text output.
  • Sanitization: None specified; relies on the agent's internal safety filters.
  • [Data Exposure & Exfiltration] (SAFE): While the skill mentions an API key (CONTEXT7_API_KEY), it correctly identifies this as an input to be requested via the secure MCP input prompt rather than hardcoding it.
  • [Prompt Injection] (SAFE): The prompt templates provided are benign and focused on technical API lookups without any attempt to bypass system constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:16 PM