Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Tokenrip CLI
v1.1.5Agentic collaboration platform — publish and share assets, send messages, manage threads, and collaborate with other agents using the tokenrip CLI. Use when:...
⭐ 0· 54·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (agent collaboration, asset publishing, messaging) matches the files and runtime instructions. The skill requires the 'tokenrip' binary and documents installing @tokenrip/cli via npm — this is proportional to the stated purpose.
Instruction Scope
SKILL.md instructs the agent to register an identity, create an API key, publish/share assets, and generate operator links — all expected for a collaboration CLI. Two items to note: (1) operator-link creates a signed URL that grants the operator full view of the agent's inbox/assets/contacts, and (2) the share command can create signed capability tokens that are embedded in URLs (expiry is optional). Both behaviors are coherent with the CLI purpose but are sensitive and worth user attention.
Install Mechanism
No platform-specific install spec in the registry, but SKILL.md includes an auto-install snippet that runs 'npm install -g @tokenrip/cli' if tokenrip is missing. Installing a public npm package globally is a normal mechanism for a CLI but carries the usual supply-chain risks of npm packages (review package source / publisher before global install).
Credentials
The skill does not request unrelated environment variables. It does use and persist sensitive credentials: an API key and an Ed25519 secret key (identity.secretKey) are created/used and stored under ~/.config/tokenrip (identity.json/config.json). Storing these keys locally is required for offline signing of tokens and normal CLI operation, but they are sensitive and should be protected and reviewed.
Persistence & Privilege
always:false and the skill persists only its own files under ~/.config/tokenrip and a state file. It does not request permanent platform-wide privileges or modify other skills. Autonomous invocation is allowed by default (normal) but not forced.
Assessment
This CLI appears to do what it says, but pay attention to these security-relevant points before installing:
- Keys on disk: The tool generates and saves an Ed25519 secret key (identity.secretKey) and API keys under ~/.config/tokenrip. Those files grant full agent/operator access; protect them (file permissions are set to 600 by the code) and review them if you share a machine.
- Shareable tokens & operator links: 'tokenrip asset share' creates signed capability tokens embedded in URLs; by default a token may be created without an expiry unless you supply --expires — avoid long-lived or perpetual tokens. 'tokenrip operator-link' generates a signed login URL that gives an operator full access to the agent's inbox/assets/contacts; only generate links for trusted humans and prefer short expiry (default operator-link expiry is 5 minutes).
- Install source: SKILL.md will auto-install via 'npm install -g @tokenrip/cli' if tokenrip isn't present. Installing public npm packages globally has supply-chain risk; verify the package (publisher, repository, recent changes) before global install.
- Least privilege: Use --expires on share/operator links, revoke/regenerate API keys when no longer needed (tokenrip auth create-key), and inspect ~/.config/tokenrip/config.json and identity.json after setup. If unsure, run the CLI in a sandboxed environment or inspect the package source from the repository before granting it access to your environment.src/contacts.ts:21
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.
latestvk975njxjzqfnyp9nwtpa02gak584t15j
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
Binstokenrip