Permission Manifest Guard

Inspects an OpenClaw skill directory before install or execution, translates declared and observed requirements into a human-readable permission manifest, an...

This skill appears coherent and implements a static permission manifest generator. Before running it: 1) Understand that its analysis is static only — it cannot see runtime behavior or transitive dependency actions; treat the manifest as an aid, not a proof. 2) The CLI will write permission-manifest.json into the inspected directory — run it on a copy or in a sandbox if you don't want repository files modified. 3) Inspect package.json dependencies (js-yaml) and run standard checks (npm install in an isolated environment, npm audit) if you plan to build/run locally. 4) Note the repository includes a CLAUDE.md that mentions an external 'saturnday' governance tool — that's documentation and not executed by the tool, but verify any external governance workflow separately. 5) If you need runtime/supply-chain guarantees (transitive dependency behavior, network reachability), use dynamic or dependency-specific scanners in addition to this tool.

Type: OpenClaw Skill Name: permission-manifest-guard Version: 0.1.1 The 'permission-manifest-guard' skill is a static analysis security tool designed to audit other OpenClaw skills. It scans source code and metadata (SKILL.md, package.json) to identify declared versus observed permissions, such as network domains, shell commands, and environment variables. The logic in 'src/extract.ts' and 'src/classify.ts' uses regex-based heuristics to detect risky capabilities (e.g., eval, child_process) and calculate a risk score. The tool's behavior is transparent, well-documented, and lacks any indicators of data exfiltration, malicious execution, or prompt injection; it functions solely as a security guardrail for the OpenClaw ecosystem.