figure-rhetoric

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown instructions for a qualitative audit of visual data and does not contain any malicious patterns or functional code.
  • [EXTERNAL_DOWNLOADS]: No external downloads or remote script executions are specified in the workflow or instructions.
  • [COMMAND_EXECUTION]: The skill does not invoke shell commands, subprocesses, or any form of dynamic code execution.
  • [CREDENTIALS_UNSAFE]: No hardcoded credentials, API keys, or sensitive environmental paths were detected.
  • [DATA_EXFILTRATION]: There are no network operations (e.g., curl, wget, fetch) that could lead to data exfiltration; the skill operates locally on provided manuscript files.
  • [PROMPT_INJECTION]: The use of keywords like 'CRITICAL' and 'IMPORTANT' is restricted to highlighting process steps and does not attempt to override the underlying AI safety guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 02:40 PM
Security Audit — agent-trust-hub — figure-rhetoric