exa-search

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted external content, creating a vulnerability to indirect prompt injection.\n
  • Ingestion points: Data is ingested from the Exa API through scripts/exa_search.py and scripts/exa_contents.py which fetch content from arbitrary web URLs.\n
  • Boundary markers: The skill lacks explicit boundary markers or delimiters to isolate untrusted web content from the agent's instructions.\n
  • Capability inventory: The skill includes Python scripts capable of making network requests to the Exa API endpoints.\n
  • Sanitization: No evidence of sanitization or filtering of retrieved web content was found within the provided scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 05:43 PM