Back to skill
Skillv1.0.0

ClawScan security

Cron Forge · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 9, 2026, 8:58 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill is an instruction-only cron-template helper; its files, instructions, and required capabilities align with the described purpose and request no extra credentials or installs.
Guidance
This skill appears coherent and low-risk: it only provides cron templates and example openclaw CLI usage and requests no secrets. Before installing, verify you trust the author/source (homepage is missing), ensure the OpenClaw CLI is the expected tool on your system, and test cron expressions in a safe environment. Remember that the agent could autonomously run openclaw cron commands if allowed by your agent policy — ensure the agent's execution permissions and the scheduled tasks themselves do not perform sensitive operations or expose secrets.

Review Dimensions

Purpose & Capability
okName/description promise simple cron templates and OpenClaw integration; SKILL.md and README provide templates and example openclaw CLI commands only. No unrelated credentials, binaries, or capabilities are requested. (Source is listed as unknown/homepage none but that affects provenance, not internal coherence.)
Instruction Scope
okRuntime instructions are limited to providing cron expressions, template files, and example openclaw cron CLI commands (openclaw cron add/list/remove). The instructions do not direct reading arbitrary system files, exfiltrating data, or contacting third‑party endpoints.
Install Mechanism
okNo install spec and no code files — instruction‑only skill. Nothing is downloaded or written to disk by the skill package itself.
Credentials
okThe skill declares no required environment variables, credentials, or config paths. The README notes the software processes/stores data locally when used, which is informational and consistent with the function.
Persistence & Privilege
okalways is false and there are no special persistence or system-modifying instructions. The skill can be invoked autonomously by the agent (platform default), which is expected for a helper that can call openclaw CLI commands.