Back to skill
Skillv1.0.1

ClawScan security

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

Scanner verdict

BenignMar 9, 2026, 7:54 AM
Verdict
Benign
Confidence
high
Model
gpt-5-mini
Summary
The skill is instruction-only and its requested resources and runtime instructions match the stated purpose of helping users build and rehearse presentations.
Guidance
This is an instruction-only presentation helper and appears coherent with its stated purpose. Before using it, avoid pasting highly sensitive or confidential data into prompts (financial secrets, unpublished IP, personal data) because any content you provide will be handled by the agent and may be logged by the platform. Because the registry lists no install artifacts, the skill will not execute new code on your machine — the main privacy risk is the content you share with the agent. If you need to use confidential slides, consider redacting or summarizing sensitive elements and verify your platform's data retention and sharing policies. If provenance matters to you, note the registry owner ID and the skill metadata (author/homepage in skill.json) and verify the publisher before wide deployment.

Review Dimensions

Purpose & Capability
okName, description, and declared capabilities (narrative building, slide structure, speaker notes, Q&A prep, delivery coaching) align with the SKILL.md and examples; there are no unrelated env vars, binaries, or install steps requested.
Instruction Scope
okSKILL.md and heartbeat.md limit actions to asking the user questions, constructing narratives, outlining slides, writing speaker notes, generating anticipated questions, and providing practice/checklist guidance. There are no instructions to read local files, access system credentials, or call unexpected external endpoints.
Install Mechanism
okNo install spec and no code files beyond documentation; nothing is written to disk or fetched during installation — lowest-risk delivery model for a skill of this type.
Credentials
okThe skill requests no environment variables, credentials, or config paths. The scope of data requested (presentation content provided by the user) is proportional to the skill's purpose.
Persistence & Privilege
okalways is false and model invocation is allowed (the platform default). The skill does not request permanent presence or system-wide configuration changes.