Back to skill
Skillv1.0.0
ClawScan security
Diddy Party · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 18, 2026, 11:31 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only persona skill that only re-styles the assistant's voice and sub-agent naming; it requests no credentials, no installs, and its instructions are consistent with its stated purpose.
- Guidance
- This skill simply changes the assistant's voice and local naming conventions; it does not request secrets or install software. Before enabling, decide whether you want the stylistic behavior (it will call the user 'Boss' by default and rename sub-agents). Test activation/deactivation phrases to ensure it returns to normal mode when requested. As with any new skill, if the registry later adds code, env requirements, or install steps, re-review those changes before trusting it with sensitive tasks.
Review Dimensions
- Purpose & Capability
- okThe name/description (party-host persona) matches the SKILL.md: it only defines voice, aliases, and response patterns. No unrelated permissions, env vars, or binaries are requested.
- Instruction Scope
- okRuntime instructions are limited to persona behavior, alias naming, response patterns, activation/deactivation phrases, and a short optional system snippet. They do not instruct reading files, accessing environment variables, network endpoints, or other system state.
- Install Mechanism
- okNo install spec and no code files — nothing is written to disk or downloaded. This is the lowest-risk install profile.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths; that is proportional to a persona-only skill.
- Persistence & Privilege
- okalways is false and the skill is user-invocable. Model invocation is allowed (the platform default) but the skill does not request persistent system-level privileges or modify other skills.