Skill flagged — suspicious patterns detected

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

Core Capabilities

v1.0.0

工作助手核心能力集成 - 包含 Obsidian/Git 同步、记忆数据库、自然语言查询、监控页面等完整能力套件。当用户需要查询系统能力、使用 Obsidian、管理记忆、查看状态时使用此技能。

0· 37·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Suspicious
high confidence
!
Purpose & Capability
The name/description and metadata claim a suite of local capabilities (Obsidian/Git sync, memory DB, query agent, monitoring). That purpose would legitimately require the scripts and tools the docs reference (memory_query_agent.py, monitor_server.py, obsidian-cli, etc.). However the published package contains only documentation files (SKILL.md, README.md, metadata.json, etc.) and no code files or explicit install instructions to provide those binaries — an implementation mismatch.
!
Instruction Scope
SKILL.md instructs the agent/operator to run local commands (python3 memory_query_agent.py, python3 monitor_server.py, obsidian create, git add/commit/push, pkill -f monitor_server, check crontab, tail logs) and references local files (/tmp/monitor_server.log, logs/memory_sync.log, memory.db, ~/.openclaw/workspace). Those actions are local and expected for the described capabilities, but the docs ask the user to run commands that rely on code and data not included in the skill, and include potentially impactful actions (git push, pkill) that could modify system state or transmit data to remote git remotes.
Install Mechanism
There is no install specification (instruction-only), which is low-risk from an auto-install perspective. However, because no code is bundled and no install instructions are provided, the skill cannot actually implement its claimed features without out-of-band components.
Credentials
The skill declares no required environment variables or credentials, which is coherent. But the workflow relies on external systems (git remote push, Obsidian Sync potential future integration, crontab) that implicitly require credentials or network access (SSH/git credentials). These credentials are not declared or explained, which is a gap that could lead users to accidentally exfiltrate data via git pushes if remotes are misconfigured.
Persistence & Privilege
The skill does not request 'always' presence and leaves autonomous invocation enabled (the platform default). It does not claim to modify other skills or system-wide agent settings. No elevated persistence privileges are requested in the metadata.
What to consider before installing
This package is documentation-only: it describes services and scripts (memory_query_agent.py, monitor_server.py, memory.db, obsidian-cli) but does not include them. Before installing or following its instructions: 1) Do not run git push/remote commands or pkill blindly — verify the repository remote and intent first. 2) Ask the publisher for the actual code or an install script, or obtain the referenced binaries from trusted sources. 3) Inspect memory.db and any logs for sensitive data before syncing or pushing. 4) If you must test, run in an isolated sandbox/container and do not expose secrets (SSH keys, tokens). 5) Prefer skills that include their implementation or clear, verifiable install steps and a homepage/author identity. If the publisher cannot provide the missing scripts or a trusted install process, treat this skill as incomplete and avoid using it in production.

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

latestvk97d54ww02rzrhwcnmsx05m97h84q3zq

License

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

Comments