Agent Memory 1.0.0
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is a local persistent-memory skill that appears purpose-aligned, but users should be aware it can save conversation-derived facts and reuse them in future sessions.
This skill looks coherent and local-only based on the provided artifacts. Before installing, decide what kinds of facts your agent is allowed to save, avoid putting passwords or sensitive secrets into memory, and review or prune the local database if memories become outdated or inappropriate.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
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.
Private, incorrect, or outdated memories could persist and influence future agent behavior if the user or agent stores them carelessly.
The skill explicitly stores conversation-derived facts and lessons in a persistent local database and recommends reloading them into future sessions.
On session start: Load recent lessons... Recall relevant facts... On session end: Extract durable facts from conversation... Default: `~/.agent-memory/memory.db`
Use this only for information you want retained across sessions, avoid storing secrets, and periodically review or delete stale memories.