Back to skill
Skillv1.0.0

ClawScan security

conceive-short-drama-en · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 6, 2026, 4:21 AM
Verdict
Benign
Confidence
high
Model
gpt-5-mini
Summary
This is an instruction-only creative writing skill whose requested capabilities and instructions are consistent with its stated purpose and do not ask for credentials, installs, or unrelated system access.
Guidance
This skill appears safe from a security/integrity perspective: it is instruction-only, asks for no credentials, and does not install code or access system files. Before installing, verify the source if you require provenance/auditability and consider whether you want the agent to invoke the skill autonomously (the skill is allowed to, by default). Also review content and moderation expectations (tone, avoidance of sensitive topics) to ensure outputs meet your editorial or policy requirements.

Review Dimensions

Purpose & Capability
okThe name and description (generate uplifting short drama plot outlines) match the SKILL.md instructions. The skill requires no binaries, env vars, or config paths—appropriate for a pure text-generation tool.
Instruction Scope
okSKILL.md contains detailed, bounded instructions for producing narrative outlines (structure, element selection, content rules). It does not instruct reading files, accessing environment variables, contacting external endpoints, or performing system actions outside text generation.
Install Mechanism
okNo install spec or code files are present; this is instruction-only which minimizes on-disk execution risk.
Credentials
okThe skill declares no required environment variables, credentials, or config paths. Nothing in the instructions requests secrets or unrelated service access.
Persistence & Privilege
okFlags show normal defaults (always:false, user-invocable:true). The skill does not request permanent presence or privileged modifications to other skills/configuration.