Markdown Memory

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This looks like a purpose-aligned local memory skill, but it keeps persistent user/agent context and references local helper scripts that are not included in the artifact.

Install this only if you want an assistant with persistent local memory. Keep sensitive secrets out of the memory files, periodically review what has been saved, and verify any local Python helper scripts before running the setup, add, search, or init commands.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

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.

#ASI06: Memory and Context Poisoning

Medium

What this means

Anything saved in these memory files may shape future responses and could expose private preferences or personal details if the files are shared or mishandled.

Why it was flagged

The skill is designed to reload persistent user, persona, and long-term memory files into future sessions. This is expected for a memory skill, but it means stored content can affect later agent behavior and may contain sensitive personal information.

Skill content

每次新会话开始时：
1. 读取 `SOUL.md` — AI 人格
2. 读取 `USER.md` — 用户信息
3. 读取 `memory/YYYY-MM-DD.md` (今天 + 昨天)
4. **主会话**：读取 `MEMORY.md`

Recommendation

Review and edit MEMORY.md, USER.md, SOUL.md, and daily memory files regularly; avoid storing passwords or secrets; and add clear rules for when memory should be saved, changed, or deleted.

#ASI04: Agentic Supply Chain Vulnerabilities

Low

What this means

If a script at that path is missing, stale, or replaced by untrusted code, running it could affect local memory files or other accessible data.

Why it was flagged

The skill instructs users to run local helper scripts for memory operations, while the provided artifact set contains only SKILL.md and no script files. This is a provenance gap rather than evidence of malicious behavior.

Skill content

python3 ~/.openclaw/workspace/scripts/memory-system/context-memory.py init

Recommendation

Before running the Python helper scripts, confirm where they came from and inspect their contents or install them from a trusted source.