exa-x-search

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious code, obfuscation, or unauthorized access patterns were detected. The skill functions as a legitimate tool wrapper for a search service.
  • [PROMPT_INJECTION]: The skill processes untrusted content from X/Twitter search results, presenting a surface for potential indirect prompt injection. 1. Ingestion points: Search results returned by the exa-search.web_search_advanced_exa tool. 2. Boundary markers: The skill specifies an output format (Results, Sources, Notes) but lacks explicit delimiters or instructions to ignore embedded commands in the fetched data. 3. Capability inventory: The skill uses the mcporter call syntax to execute MCP tools. 4. Sanitization: No specific sanitization or filtering logic is mentioned for the retrieved tweet content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 07:02 AM