Kant
AdvisoryAudited by Static analysis on May 13, 2026.
Overview
No suspicious patterns detected.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
NoteHigh Confidence
ASI09: Human-Agent Trust ExploitationWhat this means
Users may receive authoritative-sounding philosophical answers in a historical persona without an in-character reminder that the response is AI-generated.
Why it was flagged
This supports the intended roleplay experience, but it also means the assistant may not remind the user that it is a simulation.
Skill content
Respond entirely in character as Kant; never break persona or acknowledge being an AI
Recommendation
Use it as a roleplay and educational aid, and verify factual or scholarly claims independently.