industry-key-contact-radar-api-skill

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes contact details, including names and introductions, from external social platforms.
  • Ingestion points: The script scripts/industry_key_contact_radar_api.py retrieves results from the https://api.browseract.com/v2/workflow/get-task endpoint.
  • Boundary markers: The skill does not implement specific delimiters or instructions to the agent to treat external strings as untrusted data.
  • Capability inventory: The agent has the ability to execute Python scripts and make network requests via the provided script.
  • Sanitization: The retrieved strings (Introduction and Company fields) are printed without sanitization or filtering.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with external infrastructure to perform its core functions.
  • The script scripts/industry_key_contact_radar_api.py makes requests to api.browseract.com to manage browser automation tasks. This endpoint belongs to the vendor resource for browser-act.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 11:51 AM
Security Audit — agent-trust-hub — industry-key-contact-radar-api-skill