Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

openclaw memory opportunity

v1.0.0

OpenClaw Memory-OS - Digital immortality service with conversation memory extraction | 数字永生服务与对话记忆自动提取

0· 46·0 current·0 all-time
byJustin Liu@zhenstaff
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The name/description (local conversation-memory, digital-immortality) aligns with the actions described: local JSON storage, file collectors, and a CLI. Requiring node/npm and an npm package is reasonable for an npm-based CLI. However, the SKILL.md asserts 'no network activity' at runtime but the installation instructions recommend 'npm install -g' or 'git clone' which require network access — a discrepancy between claimed runtime behavior and installation steps.
!
Instruction Scope
Runtime instructions include an AUTO-TRIGGER that will automatically extract and store information when conversational trigger words are used; this implies the agent may capture and persist user utterances without an explicit per-item confirmation unless the user disables auto-trigger. The CLI also supports recursive directory scanning and bulk collect operations which can read large numbers of user files (including sensitive ones) if broad paths are supplied. The SKILL.md repeatedly advises careful use, but the instructions grant broad discretion to read and store arbitrary files and conversation content.
!
Install Mechanism
No platform install spec in the registry metadata, but SKILL.md requires installing an npm package (openclaw-memory-opportunity) and/or git-cloning the repo. Fetching via npm or git involves network downloads; the package is referenced with a GitHub repo and a commit hash (a positive signal), but installing arbitrary npm packages is moderate risk and the instructions rely on network-accessed third-party code despite claiming the runtime is offline.
Credentials
The skill declares no required environment variables, no API keys, and no required config paths. This is proportionate to the stated current capabilities (local-only storage and collection). There is no request for unrelated credentials or secrets in the manifest or SKILL.md.
Persistence & Privilege
The skill does not require 'always: true' and is user-invocable; however auto-trigger behavior plus autonomous invocation (platform default) means the skill can automatically persist memories to ~/.memory-os/ during conversations. This is coherent with its purpose but increases blast radius if you enable autonomous invocation or the auto-trigger feature without restrictions.
What to consider before installing
This skill is mostly consistent with being a local, file-based memory collector, but take these precautions before installing or enabling auto-trigger: 1) Understand installation will likely download code (npm / git) — inspect the package source (the referenced GitHub repo and commit) before installing. 2) Test in a sandbox or VM first and monitor network activity during install/use. 3) Disable AUTO-TRIGGER until you are comfortable; verify exactly what the skill will persist when it detects 'remember' / '记住' triggers. 4) When using 'collect', pass narrow explicit paths and avoid broad directories (e.g., do not point it at your entire home directory). 5) Inspect the stored JSON files under ~/.memory-os/memories/ and remove them (rm -rf ~/.memory-os/) if you no longer want the data. 6) If you need stronger protections, consider encrypting the store or only installing from a vetted local copy of the repo rather than npm. If you want me to, I can: (a) list the exact files to review in the GitHub repo, (b) draft a safe install checklist, or (c) help build a minimal test command set to validate the 'no-network' claim.

Like a lobster shell, security has layers — review code before you run it.

latestvk97a9xdmch8e6yjet1c9yczbqs83kg7c

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments