Cognition Evolution

AdvisoryAudited by Static analysis on May 2, 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.

What this means

Information or judgments from a conversation may be remembered and influence future responses, even if the user did not manually ask to save that specific item.

Why it was flagged

The skill is designed to automatically save lessons from each conversation and reuse them in future sessions, creating persistent context that could include sensitive or mistaken conclusions.

Skill content
全自动,无需干预。每次会话结束后自动触发。 ... 沉淀为可复用原则,下次遇到同类问题自动调用
Recommendation

Use it only when you want automatic long-term learning; review saved summaries for accuracy and sensitivity, and avoid enabling it for confidential conversations unless memory controls are available.