Skillv1.0.0

ClawScan security

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

Scanner verdict

BenignMar 26, 2026, 7:37 AM

Verdict: benign
Confidence: medium
Model: gpt-5-mini
Summary: The skill's declared purpose (convert PDFs/topics into notes, quizzes, slides, mindmaps and audio) matches its instructions and it requests no credentials or installs, but the runtime tooling and some steps are underspecified (how images, audio and PPTX are actually produced), so confirm platform capabilities before use.
Guidance: Before installing: 1) Confirm the host platform provides the toolchain the skill implicitly needs (image generation/editing, TTS for MP3, PDF→PPTX compilation) or whether you'll need to supply API keys/binaries. 2) Ask the skill author to clarify what gen_images/edit_images calls map to and how PPTX/mp3 are produced (local binaries vs external APIs). 3) Consider privacy: if you ask the skill to "search and generate", it may fetch external web content — avoid uploading sensitive student materials unless you know where outputs and source files are stored. 4) Request example output files (a sample notes PDF, quiz HTML, and one slide deck) to validate formatting constraints (colors, interactivity, no inline previews). 5) If you require offline or on-prem generation for compliance, verify the runtime environment can perform image/audio/PPTX generation without sending data to third-party services.

Review Dimensions

Purpose & Capability: okThe skill's name/description align with the instructions: it processes uploaded PDFs or a user-provided topic and produces notes, quizzes, slides, mindmaps and audio. It does not request unrelated credentials or config paths. One minor gap: the SKILL.md assumes the ability to generate and compile images, MP3 and PPTX but does not declare required binaries or services (e.g., image model, TTS, PDF/PPTX generator). This is plausibly platform-provided but is underspecified.
Instruction Scope: noteInstructions remain within the claimed scope (parse content, extract structure, generate specified artifacts). However the document references functions/tools by name (gen_images, edit_images) and compilation steps (compile to PDF/PPTX, produce MP3) without specifying how these should be executed or what external endpoints/APIs/binaries are used. Also the ‘help me search and generate’ fallback allows the agent to fetch web content — expected for the task, but it broadens the attack surface and privacy considerations.
Install Mechanism: okThere is no install spec and no code files — instruction-only skills have minimal disk footprint and no automatic downloads. This is low risk from an install point of view.
Credentials: okThe skill requests no environment variables, credentials, or config paths, which is proportionate for the declared functionality. Note that generating audio, PPTX or invoking external image models might normally require service keys or binaries; none are requested here, so confirm where generation will run and whether keys are needed at runtime.
Persistence & Privilege: okThe skill is not always-included and does not request elevated persistence or modifications to other skills. Autonomous invocation is allowed (platform default) but that is not combined with other privileged or broad credential access.