exa-search
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by searching the web and extracting content from arbitrary URLs, which could contain instructions designed to influence the agent's behavior.
- Ingestion points: The scripts
scripts/exa_search.pyandscripts/exa_extract.pyretrieve web content (titles, text, and highlights) from external sources via the Exa API. - Boundary markers: The prompt instructions in
references/web-search.mdandreferences/web-extract.mddo not include explicit delimiters or instructions for the agent to ignore directives embedded within the retrieved data. - Capability inventory: The skill has the capability to search the internet, fetch remote URL content, and write results to local JSON files (
-oflag). - Sanitization: No sanitization or filtering of the retrieved web content is performed before it is presented to the agent for synthesis and citation.
Audit Metadata