Skillv1.0.0

ClawScan security

个人品牌故事 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignMar 1, 2026, 5:26 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill's files and runtime instructions are coherent with its stated purpose (generating personal brand stories); it has no installs or credential requirements, but the instructions ask the agent to collect sensitive personal details so users should consider privacy and consent before use.
Guidance: This skill appears to be what it claims: a template-driven personal-brand storyteller. Before installing or using it, consider privacy and consent: the SKILL.md directs the agent to collect specific, potentially sensitive personal details (salaries, medical events, exact dates, testimonials). Only share what the user explicitly consents to; anonymize or redact PII/medical details when possible; avoid collecting or storing third-party private data without permission. If you plan to publish stories that quote others or use testimonials, verify and obtain permission. Because the skill is instruction-only, there is no hidden code risk, but also no code review — monitor what data the agent logs or transmits in your environment and restrict export of sensitive fields. If you want stronger guarantees, ask the skill author to add explicit guidance about consent, retention, and redaction of sensitive inputs.

Purpose & Capability: okName/description and all included files (SKILL.md, templates, reference, example story) consistently describe producing personal-brand narratives using a 5-step framework. There are no requested binaries, env vars, or installs that are unrelated to this purpose.
Instruction Scope: noteRuntime instructions explicitly direct the agent to interview users and gather highly specific personal data (exact salaries, dates, names, health events, testimonials, timelines, case-study numbers). That data collection is relevant to producing authentic stories, but it is privacy-sensitive (PII and medical details) and the SKILL.md does not mention consent, retention limits, or redaction. There's no instruction to read system files or external config, and no unexpected network endpoints are referenced.
Install Mechanism: okInstruction-only skill with no install spec and no code files — nothing is downloaded or written to disk. This is the lowest-risk install profile.
Credentials: okThe skill requires no environment variables, credentials, or config paths. The lack of requested secrets aligns with the stated purpose.
Persistence & Privilege: okalways:false and default autonomy settings. The skill does not request permanent presence or modify other skills; nothing in the package grants elevated agent privileges.