What problem does it solve?
Operators running Picoclaw agent environments need a local, read-only way to review their security posture without modifying configuration or sending data over the network. This Skill turns a generated Picoclaw posture profile into severity-ranked findings with remediation guidance.
Core Features & Use Cases
- Posture Finding Engine: Detects critical issues such as publicly exposed Web UI, disabled UI auth, unrestricted workspace tooling, and unsigned verification mode.
- Trust-Boundary Reviews: Flags MCP server usage, scheduler persistence, plaintext secret markers, and multi-channel gateway auth for operator review.
- Deterministic Output: Emits stable, sorted JSON findings plus a severity summary count for auditing and diffing over time.
- Use Case: An operator runs the CLI against their current Picoclaw profile before exposing a gateway, receives a critical finding for a public Web UI, and binds it to localhost with auth before going live.
Quick Start
Ask the agent to run the Picoclaw posture review against your current profile at ~/.picoclaw/security/clawsec/current-profile.json and summarize the findings.