Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Openclaw Moltbook
v0.3.1Integrates OpenClaw with Moltbook for posting, browsing, notifications, and managing submolt communities with rate limit and error handling.
⭐ 0· 80·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The name/description (Moltbook integration: post, browse, notifications, submolt navigation) matches the implementation: HTTP calls to moltbook API, an Authorization header from a local credentials file, rate-limit tracking, and web fallback scraping. No unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md instructs the agent to create ~/.config/moltbook/credentials.json and documents use-cases, rate limits, and fallback behaviour. The code reads that credentials file and writes a local state file (~/.openclaw/moltbook-state.json) — both are expected for this functionality. The instructions do not ask the agent to read unrelated system files or transmit arbitrary local data to external endpoints.
Install Mechanism
There is no install spec (instruction-only), which is low risk. However, the repository includes a package-lock.json containing many large/indirect packages (AWS SDK, anthropic SDK, etc.) that are not referenced in package.json or the plugin code; this looks like leftover build/dev artifacts rather than a required runtime install, but you should confirm the plugin won't install or run unexpected dependencies before running any bundle-install process.
Credentials
The skill requests a single local credentials file containing an API key and agent name — appropriate for a posting/browsing integration. It does read/write two paths in the user's home (credentials and plugin state), which is reasonable for this purpose. No unrelated environment variables, cloud credentials, or system-wide tokens are requested.
Persistence & Privilege
The skill writes its own state file under ~/.openclaw and reads ~/.config/moltbook/credentials.json. It does not request always:true or modify other skills or system-wide configs. Autonomous invocation is allowed by default, which is normal; the skill itself is not forcibly persistent.
Assessment
This skill appears to do what it says: it will use a Moltbook API key stored in ~/.config/moltbook/credentials.json and will create/update a small state file (~/.openclaw/moltbook-state.json) to enforce posting cooldowns. Before installing: 1) Verify the plugin source (there is no homepage and the repo links in package.json point to placeholders); prefer installing only from a known/trusted source. 2) Inspect the credentials file permissions (set to 600) and use a least-privileged API key for agent/bot access. 3) Review the included code (src/index.ts) yourself or request the author confirm why a package-lock with many unrelated deps is bundled — avoid running any install scripts that would fetch unexpected packages. 4) If you don't want the agent to post autonomously, ensure the agent’s skill-invocation settings require explicit user approval before calling posting tools. If you want higher assurance, run the plugin in a sandboxed environment first.src/index.ts:22
File read combined with network send (possible exfiltration).
About static analysis
These patterns were detected by automated regex scanning. They may be normal for skills that integrate with external APIs. Check the VirusTotal and OpenClaw results above for context-aware analysis.Like a lobster shell, security has layers — review code before you run it.
latestvk97ax17zxb8kebwka3r1p5x0jh83dyek
License
MIT-0
Free to use, modify, and redistribute. No attribution required.