Memory Search
AdvisoryAudited by Static analysis on Apr 30, 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
The agent may surface or rely on remembered personal details, prior conversations, todos, names, dates, or preferences when answering.
Why it was flagged
The skill retrieves persistent memory and potentially session transcripts, which can contain sensitive personal context and can influence future answers.
Skill content
Semantic vector search across your indexed memory files (MEMORY.md, memory/*.md, and session transcripts).
Recommendation
Install only if you want the agent to use persistent memory; keep memory files accurate and avoid indexing sensitive transcripts or notes you do not want reused.