Memory Recall
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.
NoteHigh Confidence
ASI06: Memory and Context PoisoningWhat this means
Using this skill may surface private prior memories, diary entries, decisions, contacts, or conversation snippets in the current chat.
Why it was flagged
The skill explicitly instructs the agent to search persistent memory and diary files, which may contain sensitive historical conversation or personal context.
Skill content
搜索：MEMORY.md（精确） + memory/*.md（日记）
Recommendation
Use it only when you want the agent to search your stored memories, and review results before sharing them with others or pasting them into external tools.