exa-search

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill introduces a vulnerability surface for indirect prompt injection by retrieving untrusted data from the internet.\n
  • Ingestion points: Web data is ingested into the agent's context via scripts/exa_search.py, scripts/exa_contents.py, scripts/exa_research.py, scripts/exa_research_async.py, and scripts/exa_similar.py.\n
  • Boundary markers: The scripts do not automatically include delimiters or specific instructions for the agent to isolate or ignore potentially malicious content within the fetched data.\n
  • Capability inventory: The skill enables network communication with the Exa AI API (api.exa.ai) using the requests library. No dangerous capabilities such as local file writing or arbitrary command execution were found.\n
  • Sanitization: No sanitization is performed on the content retrieved from the web before it is passed to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 02:21 PM