agnes-free-text

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill transmits user-provided prompts and system instructions to the Agnes AI API endpoint at https://apihub.agnes-ai.com/v1/chat/completions. This network operation is the primary purpose of the skill and is documented for the user.
  • [DATA_EXPOSURE]: API keys are managed through environment variables (AGNES_API_KEY or AGNES_TOKEN), avoiding hardcoded secrets. The script includes a feature to write API responses to a local file via the --output-json flag, which is standard behavior for command-line utilities.
  • [COMMAND_EXECUTION]: The skill utilizes a Python script to facilitate API requests. A review of the code shows it does not invoke arbitrary shell commands or use dangerous functions such as eval, exec, or subprocess.
  • [SAFE]: No malicious patterns, such as prompt injection, code obfuscation, unauthorized privilege escalation, or persistence mechanisms, were detected across the skill's instructions or scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 01:55 PM
Security Audit — agent-trust-hub — agnes-free-text