Skillv1.0.0

ClawScan security

NotebookLM Prompts · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignMar 8, 2026, 6:14 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only prompt library for generating presentation slides; its files, requirements, and instructions are coherent with that purpose and contain no surprising installs, credential requests, or hidden behavior.
Guidance: This skill is a prompt/template pack for slide generation and appears internally consistent. Before using: (1) avoid pasting sensitive or confidential content into third‑party services (NotebookLM, Kael.im) referenced by the prompts — check their privacy policies; (2) test prompts with non-sensitive sample content to verify outputs and that formatting rules behave as expected; (3) be aware prompt sources reference public social posts (X.com) — the templates may reflect that style and any licensing/copyright norms of those designs; and (4) if you plan to automate sending user data to external services, ensure you have consent and the destination is trusted.

Purpose & Capability: okName and description match the provided assets (SKILL.md + PROMPTS.md). The skill only contains prompt templates for slide styles and asks for no binaries, env vars, or config paths — all appropriate for a prompt library.
Instruction Scope: okRuntime instructions are limited to asking the user about topic/audience, selecting and customizing a style, and feeding prompts to NotebookLM/Kael.im. The prompts themselves contain formatting/design rules but do not instruct the agent to read unrelated files, access system state, or send data to unexpected endpoints.
Install Mechanism: okNo install specification or code files are present. Being instruction-only means nothing is downloaded or written to disk by the skill itself — this is low-risk and proportionate for the stated purpose.
Credentials: okThe skill requires no environment variables, credentials, or configuration paths. There are no requests for unrelated secrets or broad access; the level of requested access is minimal and appropriate.
Persistence & Privilege: okalways is false and the skill does not request permanent presence or modify other skill/system settings. Model invocation is allowed (the platform default), which is appropriate for an interactive prompt helper.