Back to skill
Skillv0.5.0

ClawScan security

WordPress WP-CLI Internal API · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 4, 2026, 8:53 PM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill is internally consistent with its stated purpose (authoring and reviewing WP-CLI command code); it is instruction-only, requests no credentials, and contains a simple local script to render command skeletons.
Guidance
This skill appears safe and coherent for WP-CLI command development. Before running: (1) review the small render-command-skeleton.sh script (it simply prints or writes a PHP template); (2) avoid passing a --write path that could overwrite important system files—use a dev workspace or temporary path; (3) review any generated PHP before loading it into production; (4) note that autonomous agent invocation is allowed by default—if you enable the skill for automated agents, restrict what paths and write-arguments those agents may use.

Review Dimensions

Purpose & Capability
okName, description, and included files (references and a skeleton generator) align with WP-CLI command authoring. There are no unrelated binaries, env vars, or network installs requested.
Instruction Scope
noteSKILL.md stays on-purpose (read local references, use the provided script to render command skeletons, prefer WP_CLI internal helpers). The included script can write a generated PHP file to any --write path supplied by the caller, so callers/agents should avoid passing sensitive or system paths to prevent accidental overwrites.
Install Mechanism
okNo install spec or external downloads — instruction-only with a local shell script. Nothing is fetched from external URLs or written to disk by an installer.
Credentials
okThe skill declares no environment variables, credentials, or config paths. The runtime instructions only reference bundled local files and WP-CLI internal APIs appropriate to the stated purpose.
Persistence & Privilege
okalways is false and the skill does not request persistent or cross-skill privileges. Autonomous invocation is allowed by default (normal for skills) but not combined with other concerning privileges.