exa-entities

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of content from external web pages, professional profiles, and news articles via the Exa.ai API. This data represents an untrusted surface where malicious actors could embed instructions intended to influence the agent's behavior at runtime.
  • Ingestion points: Data ingestion occurs through functions such as exa.search_and_contents and exa.get_contents across references/company-search.md and references/people-search.md.
  • Boundary markers: The provided implementation patterns do not utilize delimiters or specific instructions to the agent to treat the retrieved content as untrusted data.
  • Capability inventory: The skill involves network access to the Exa.ai API and local file system operations, such as exporting data to CSV files in references/company-search.md.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the text content retrieved from external URLs before it is processed or presented to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:47 PM
Security Audit — agent-trust-hub — exa-entities