skills/team-attention/hoyeon/mirror/Gen Agent Trust Hub

mirror

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a conversational bridge to confirm user intent, serving as an alignment tool rather than an execution tool.
  • [SAFE]: Includes robust negative constraints that explicitly forbid the agent from generating plans, writing code, or executing git commands while in the 'mirror' mode.
  • [SAFE]: Tool access is limited to basic read and interaction functions (AskUserQuestion, Read, Grep, Glob) with no network or elevated privilege access.
  • [SAFE]: No patterns of obfuscation, data exfiltration, or malicious prompt injection were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 11:01 AM