extruct-api

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on a bundled CLI tool (extruct-api) to perform all API operations. This tool is resolved using absolute paths to ensure reliability and security within the execution environment.
  • [SAFE]: No malicious patterns, hardcoded credentials, or unauthorized data exfiltration techniques were detected. Network communication is limited to the official vendor domains (extruct.ai).
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing external data (e.g., company news and profiles) retrieved from the Extruct API. 1. Ingestion points: Data from companies search, deep-search results, and tables data. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are implemented. 3. Capability inventory: Command execution via the bundled CLI. 4. Sanitization: No content sanitization or validation of the retrieved API data is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 02:42 PM