OpenClaw Cost Guard

PassAudited by ClawScan on May 1, 2026.

Overview

This appears to be a local, read-only cost-audit helper, with minor notes about running Node code, limited provenance, and keeping report output private.

This skill looks safe for its stated purpose as a local OpenClaw cost-governance checker. Before installing, note that it runs Node code and reads an OpenClaw config file, so use the intended path and avoid sharing the JSON report publicly if it contains budget or local path details.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

The skill may inspect your local OpenClaw configuration when used for a cost review.

Why it was flagged

The bundled script reads a default or user-selected OpenClaw config file. This is central to the cost-audit purpose and appears read-only, but it is still local code execution with local file access.

Skill content
const configPath = path.resolve(getArg('--config', path.join(os.homedir(), '.openclaw', 'openclaw.json')));
Recommendation

Run it only against the intended config file and review the report before sharing it outside your workspace.

What this means

You have less external provenance information about where the skill came from.

Why it was flagged

The skill has limited provenance and installation metadata. The provided package is small and dependency-free, so this is a transparency note rather than a behavior concern.

Skill content
Source: unknown; Homepage: none; No install spec — this is an instruction-only skill.
Recommendation

Install from a trusted source and verify the included files if provenance matters for your environment.

What this means

The output may reveal local path information or budget settings.

Why it was flagged

The report includes derived evidence such as the config path and detected budget values. This is useful for the audit, but those details may become part of chat or log context if copied elsewhere.

Skill content
evidence.budgetHints = budgetHints; ... console.log(JSON.stringify({ score, verdict, summary, findings, recommendations, guardrails, evidence }, null, 2));
Recommendation

Treat the generated JSON as internal and redact path or budget details before sharing it externally.