Back to skill
Skillv1.0.0
ClawScan security
Starz · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 28, 2026, 12:04 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only skill that provides a short research/analysis brief about the Starz streaming service; it requests no secrets, installs, or system access and appears internally consistent with its stated purpose.
- Guidance
- This skill is an instruction-only, read-only briefing about Starz and appears safe from a security standpoint — it asks for no credentials or installs. Consider that the content is an editorial summary: verify facts against primary sources if you need authoritative data or commercial decisions. If you plan to let an agent invoke skills autonomously, this particular skill poses minimal risk, but always review any skill that later adds network calls, installs, or environment-variable requirements before enabling it.
Review Dimensions
- Purpose & Capability
- okThe skill's name and description claim to provide analysis of Starz and the SKILL.md is exactly an editorial/analysis piece about Starz strategy and history. There are no requirements (binaries, env vars, credentials, config paths) that are unrelated to that purpose.
- Instruction Scope
- okSKILL.md contains only written guidance and a research/read_when list; it does not instruct the agent to run commands, read files, access environment variables, or transmit data to external endpoints. Scope remains limited to producing/using the included analysis.
- Install Mechanism
- okNo install spec or code files are present. As an instruction-only skill, nothing is written to disk or fetched at install time.
- Credentials
- okThe skill requests no environment variables, credentials, or config paths. There are no extra or unexplained secret requirements.
- Persistence & Privilege
- okThe skill does not request always:true and uses platform defaults; it does not modify other skills or system settings. Autonomous invocation is allowed (platform default) but the skill's content-only nature keeps its blast radius minimal.