Back to skill
Skillv1.0.0
ClawScan security
Short Video Hook Crafter · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 27, 2026, 12:23 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only creative helper whose declared requirements and runtime instructions are coherent with its purpose and request no sensitive privileges or installs.
- Guidance
- This skill is low-risk: it's documentation-only and requires no network, installs, or credentials. If you care about provenance, note the source/homepage are unspecified — that is not a technical risk here but means there is no publisher reputation to check. Also remember the safety disclaimer: the skill can produce persuasive/attention-grabbing language but you remain responsible for ensuring hooks comply with platform policies and truthful representation. If you want to be extra cautious, review SKILL.md yourself before enabling autonomous invocation, but there are no technical red flags.
Review Dimensions
- Purpose & Capability
- okName/description (craft short-video hooks) match the provided assets: SKILL.md contains only guidance, no binaries, env vars, or APIs are required — nothing requested appears unrelated to the stated purpose.
- Instruction Scope
- okSKILL.md is a self-contained workflow for generating hooks, examples, inputs, and outputs. It does not instruct the agent to read files, access credentials, make network calls, or transmit data to external endpoints.
- Install Mechanism
- okNo install spec and no code files are present (instruction-only). This minimizes on-disk execution risk and there are no external download/install steps.
- Credentials
- okNo environment variables, credentials, or config paths are requested. The skill does not ask for unrelated secrets or wide-reaching access.
- Persistence & Privilege
- okSkill is not set to always:true and does not request system or other-skills modifications. disable-model-invocation is default false (agent may call it autonomously), which is normal for descriptive skills.