ai-chat
Warn
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- EXTERNAL_DOWNLOADS (MEDIUM): The skill contains 11 instances of 'curl' commands fetching content from 'https://fullstackrecipes.com'. This domain is not on the list of trusted external sources, which increases the risk of retrieving malicious scripts or instructions.\n- COMMAND_EXECUTION (LOW): Direct use of 'curl' in the documentation encourages the agent to execute shell commands to interact with external web services.
Audit Metadata