Back to plugin

Security audit

Language Boundary

Security checks for vulnerabilities and agentic risk

Overview

This plugin is a disclosed OpenClaw safety guardrail that logs local audit/state data and controls risky agent actions, with some privacy and packaging caveats users should review.

Install only if you want a high-authority safety plugin that can observe and gate agent actions. Review the audit/state paths first, keep redaction enabled, disable audit or relocate logs in sensitive environments, and avoid running release/development scripts on machines where build side effects or unpinned dev tooling are unacceptable.

SkillSpector was not run because this plugin release contains no bundled skills.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/release-check.ts:174
Evidence
execFileSync(cmd, args, { cwd: ROOT, encoding: "utf8", stdio: ["ignore", "pipe", "pipe"], timeout: 180_000 });

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/reliability-smoke.ts:105
Evidence
const stdout = execFileSync(cmd, args, { cwd: opts.cwd, encoding: "utf8", timeout: opts.timeoutMs ?? 10_000, stdio: ["ignore", "pipe", "pipe"] });