skills/wkentaro/skills/hear-me/Gen Agent Trust Hub

hear-me

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns such as data exfiltration, obfuscation, or unauthorized command execution were detected.
  • [PROMPT_INJECTION]: The skill utilizes a persistent state ('dictation mode') within the conversation to apply a specific readback protocol to subsequent messages. This behavior is explicitly controlled by the user via 'on' and 'off' commands.
  • [CREDENTIALS_UNSAFE]: The skill instructions proactively direct the agent to identify and mask sensitive values like API tokens in its output, reducing the risk of accidental credential exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 06:29 AM
Security Audit — agent-trust-hub — hear-me