Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Openclaw Plugin
v0.3.9Precision decisioning, agentic trust, and verifiable identity for autonomous agents
⭐ 0· 60·0 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 skill claims to gate high-risk tool calls and produce attestations; the included code implements before_tool_call and after_tool_call hooks, a client that POSTs to a governance gateway, and two callable tools (kevros_verify, kevros_passport). Requiring an API key for the governance gateway is consistent with its purpose.
Instruction Scope
The runtime instructions and code send tool inputs and truncated outputs (and release tokens/metadata) to https://governance.taskhawktech.com via /governance/verify and /governance/attest. This is coherent for a governance plugin but is privacy-sensitive because tool inputs/outputs (even truncated) are transmitted off-host. The SKILL.md and README state that raw payloads are SHA-256 hashed server-side, but the client code transmits raw action_payloads — the claim depends on the gateway behavior, not client-side enforcement.
Install Mechanism
The package is distributed as an npm package (@kevros/openclaw-plugin) and the repository field points to a GitHub URL; included files contain source and built dist files. No binary downloads or obscure URLs are used. The registry metadata lacking an explicit install spec is a minor inconsistency with the SKILL.md (which lists an npm install) but not a high risk.
Credentials
Registry metadata lists KEVROS_API_KEY as a required primary env var which is appropriate, but the code auto-provisions a free API key by calling POST /signup if no apiKey is configured. That makes the environment requirement optional in practice; the mismatch should be clarified. No other unrelated credentials or config paths are requested.
Persistence & Privilege
The skill does not request always:true and does not modify other skills' configs. It registers hooks and tools within the agent API as expected. The client caches an auto-provisioned API key only in memory for the session; it does not write persistent credentials to disk in the provided code.
Assessment
This plugin appears to implement what it claims — it will intercept high-risk tool calls and POST verification/attestation data to governance.taskhawktech.com. Before installing: (1) Confirm you trust the external gateway (review their privacy policy, source repo, and the gateway URL) because agent inputs/outputs (possibly sensitive) are transmitted off-host; (2) Test in advisory mode (mode: "advisory") first to avoid fail-closed blocking and to see what data would be sent; (3) Prefer providing your own KEVROS_API_KEY in config rather than allowing the plugin's auto-signup if you want control over provisioning and rate limits; (4) Consider restricting highRiskTools to only the truly sensitive tools for your deployment; (5) If you need stronger guarantees, verify the gateway implementation (server-side handling of payload hashing and storage) before sending production data.Like a lobster shell, security has layers — review code before you run it.
latestvk970pcv2sbfqp499jhsx2cdhkh839g1h
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
OSLinux · macOS · Windows
EnvKEVROS_API_KEY
Primary envKEVROS_API_KEY