context7

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions utilize curl and jq to perform network requests and process JSON data from the Context7 API. These are standard system utilities used within the skill's defined workflow for data retrieval.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest documentation content from a third-party API (context7.com), creating a vulnerability surface where malicious instructions could be embedded in the retrieved data.
  • Ingestion points: External documentation fetched via the /api/v2/context endpoint as described in SKILL.md.
  • Boundary markers: None identified. The skill does not provide instructions to wrap the external content in delimiters or warn the agent to ignore instructions within the retrieved documentation.
  • Capability inventory: The skill uses curl for network operations and jq for output formatting.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the fetched documentation before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:29 PM
Security Audit — agent-trust-hub — context7