Openclaw Waste Audit

PassAudited by ClawScan on May 16, 2026.

Overview

This is a coherent OpenClaw waste-audit helper, but it will inspect local cron logs and run local diagnostic commands, and any suggested cron edits should be reviewed before approval.

This skill appears safe for its stated purpose if you want an OpenClaw cron/token waste audit. Expect it to inspect local OpenClaw logs and possibly run local diagnostic tools. Do not approve any cron edit commands until you have reviewed the affected job, schedule, and rollback plan.

Findings (4)

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.

Low

#ASI05: Unexpected Code Execution

What this means

Running the audit may execute local code from the user's Hermes/OpenClaw environment.

Why it was flagged

The skill directs the agent to execute an existing local diagnostic Python script that is not bundled in the provided artifacts. This is purpose-aligned for diagnostics, but the script itself was not available for review.

Skill content

python3 ~/.hermes/scripts/clawsetup_diagnostic.py
# or: python3 ~/.hermes/hermes-agent/scripts/clawsetup_diagnostic.py

Recommendation

Use this only where you trust the local ClawSetup diagnostic script; inspect that script first if the environment is unfamiliar.

Low

#ASI06: Memory and Context Poisoning

What this means

The agent may inspect and summarize details from past OpenClaw cron jobs while identifying waste.

Why it was flagged

The audit reads persisted OpenClaw cron run JSONL files, including token usage, errors, delivery fields, and summaries. This is needed for the audit but may expose sensitive operational context.

Skill content

runs_dir = os.environ.get('OPENCLAW_HOME', os.path.expanduser('~/.openclaw'))
runs_dir = os.path.join(runs_dir, 'cron', 'runs')

Recommendation

Run it only if you are comfortable letting the agent inspect OpenClaw cron logs, and avoid sharing raw audit output outside trusted contexts.

Info

#ASI03: Identity and Privilege Abuse

What this means

The audit may rely on the user's existing OpenClaw access to view job run information.

Why it was flagged

The skill may use an existing OpenClaw gateway-authenticated CLI for read-only cron inspection. The artifacts do not show credential capture or token handling.

Skill content

openclaw-env cron runs --id <job_id> --limit 3

**Note:** `openclaw cron show` requires gateway auth.

Recommendation

Confirm that the OpenClaw account/context is the one you intend to audit before running gateway-backed commands.

Low

#ASI02: Tool Misuse and Exploitation

What this means

If approved, suggested commands could persistently change OpenClaw scheduled jobs and affect cost or behavior.

Why it was flagged

The skill includes commands that could modify cron schedules, but it explicitly presents them as post-approval fixes rather than automatic actions.

Skill content

⚠️ **Read-only until approved.** Run the fix commands below only after you confirm.

**Fix commands (run only after BG approval):**
```bash
# Job 1 — reduce hourly → every 6 hours
openclaw-env cron edit <job_id> --cron

Recommendation

Review each proposed cron edit, keep a record of the old schedule, and only approve changes you understand.