exa-code-search

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill content.
  • [COMMAND_EXECUTION]: The skill utilizes a specific command-line interface (mcporter) to interact with the search tool as intended for its functionality.
  • [PROMPT_INJECTION]: The skill interacts with external data from search results, which constitutes an indirect prompt injection surface.
  • Ingestion points: External technical documentation and code from Exa search results.
  • Boundary markers: Not present; the instructions do not include specific delimiters for search output.
  • Capability inventory: Tool access via the mcporter CLI.
  • Sanitization: No sanitization of the retrieved external content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 07:02 AM