ai-intelligence-investigator

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill is designed to automatically transmit investigation reports to the vendor's platform at redfox.hk. This is a documented feature for storing user investigation records and requires an API key provided by the user.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from multiple external sources including search engines and financial forums. 1. Ingestion points: Web search results from sources like Baidu, Google, Snowball, and EastMoney. 2. Boundary markers: None identified in the skill instructions. 3. Capability inventory: Network operations via shell commands (curl) directed to the vendor's API. 4. Sanitization: No explicit sanitization or filtering logic for external content was observed.
  • [COMMAND_EXECUTION]: The skill workflow includes instructions for the agent to use curl to send report data to a remote vendor endpoint.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 09:46 AM
Security Audit — agent-trust-hub — ai-intelligence-investigator