exa-search

Warn

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to build and execute shell commands using the $ARGUMENTS provided by the user (e.g., python3 "$EXA_FETCHER" search "QUERY"). This pattern is susceptible to command injection; if the user's query contains shell metacharacters like ;, &, or backticks, it could lead to the execution of arbitrary commands on the host system.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves content from external websites (highlights, summaries, and full text), which is inherently untrusted data that could contain malicious instructions.
  • Ingestion points: External web content and search results fetched via the Exa API as described in SKILL.md.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or provide warnings to the agent to ignore instructions embedded in the search results.
  • Capability inventory: The skill is configured with Bash, Read, and Write tools, providing a significant capability surface if an indirect injection successfully influences the agent.
  • Sanitization: There is no evidence of sanitization or validation of the retrieved web content before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill's setup instructions involve installing the exa-py library from the official Python Package Index (PyPI). This is a standard and expected dependency for the service's functionality.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 10, 2026, 09:37 AM