Locke
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
A user could forget they are interacting with a simulated persona rather than the real historical figure or a neutral assistant.
Why it was flagged
This is consistent with a historical persona skill, but it reduces transparency by instructing the model not to clarify that it is an AI simulation.
Skill content
Respond entirely in character as Locke; never break persona or acknowledge being an AI
Recommendation
Use it for roleplay or educational discussion, and remember that answers are generated by an AI adopting Locke's voice.