Back to skill
Skillv1.0.0
ClawScan security
viral-article-deconstructor · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 13, 2026, 3:15 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only skill to analyze viral articles; its declared requirements, files, and runtime instructions are coherent and proportionate to the stated purpose.
- Guidance
- This skill is low-risk from a system/credential perspective because it only contains instructions and example text. Before installing, consider: (1) privacy — avoid feeding private or sensitive documents (personally identifiable information, internal secrets, private chats) into the skill; (2) copyright — the included reference articles are copied here for analysis — respect copyright when reusing outputs; (3) ethical use — the skill helps extract persuasive and emotionally triggering language, which can be used to manipulate audiences, so use results responsibly and in line with applicable policies and laws; (4) data exfiltration check — SKILL.md does not send data to external endpoints, but if you plan to adapt the skill, review any changes that add network calls or credential usage.
Review Dimensions
- Purpose & Capability
- okName/description (viral article deconstruction) match the content: the skill provides a multi-dimensional analysis template and includes example article text. It declares no binaries, env vars, or credentials that would be unrelated to its purpose.
- Instruction Scope
- okSKILL.md instructs the agent to read and structurally analyze an article (ten analysis dimensions plus two specialized extraction tasks). It does not instruct reading system files, environment variables, or exfiltrating data to external endpoints. Example articles are included as reference files.
- Install Mechanism
- okNo install spec and no code files beyond markdown content — the skill is instruction-only, so nothing will be written to disk or downloaded at install time.
- Credentials
- okThe skill requires no environment variables, credentials, or config paths. There are no disproportionate secret requests or unrelated permissions.
- Persistence & Privilege
- okalways is false and the skill does not request elevated or persistent privileges or modify other skills/configuration. Autonomous invocation is allowed (platform default) but not combined with other red flags.