Skillv1.2.0

ClawScan security

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

BenignMar 7, 2026, 11:01 AM

Verdict: benign
Confidence: medium
Model: gpt-5-mini
Summary: The skill is an instruction-only release coordination toolkit with templates and two trivial scripts; it contains minor packaging inconsistencies (mismatched naming/version strings) but otherwise requests no credentials, performs no installs, and stays within its stated scope.
Guidance: This skill appears to do what it claims: provide checklists, report templates, and brief helper scripts. Before installing, verify two small anomalies: (1) registry metadata lists the package name as '1.2.0' (not a human-readable name) and (2) scripts/healthcheck.sh echoes 'pipiwu-benchmark-gamma-skill' — likely a copy/paste/packaging error. Confirm where the referenced CLI commands (release, workflow) are expected to come from in your agent environment; the skill does not implement them. Because it requests no credentials or installs, risk is low, but if you rely on this for production rollouts test it in a safe environment first and confirm the publisher/owner identity. If you see any added install steps, network calls, or credential prompts later, treat that as suspicious and re-evaluate.

Purpose & Capability: noteThe SKILL.md, templates, and tiny helper scripts match the stated purpose (release coordination). Oddities: top-level metadata name is '1.2.0' instead of a descriptive name, and the healthcheck script prints a different skill name ('pipiwu-benchmark-gamma-skill'), suggesting a copy/paste or packaging mistake. The SKILL.md references CLI commands (release, workflow) that are not provided by the package — this is acceptable for an instruction-only skill if those commands are provided by the environment, but you should confirm where those commands come from.
Instruction Scope: okRuntime instructions are limited to gathering release inputs, running high-level commands, and using included templates. They do not direct the agent to read unrelated files, access secrets, or send data to external endpoints.
Install Mechanism: okNo install spec; the skill is instruction-only. Provided shell scripts are trivial and only echo static text. No downloads or archive extraction occur.
Credentials: okThe skill declares no required environment variables, credentials, or config paths — consistent with its simple templates-and-instructions purpose.
Persistence & Privilege: okSkill is not always-enabled and uses default invocation settings. It does not request system-wide persistence or modify other skills' configurations.