Back to skill
Skillv1.0.0
ClawScan security
Math · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 11, 2026, 9:43 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only math tutor whose requested resources and runtime instructions align with its stated purpose and do not request extra credentials or install anything.
- Guidance
- This skill is instruction-only and coherent with its stated purpose. It's low-risk from an install/credential perspective, but remember: (1) LLMs can still make arithmetic or reasoning errors — double-check critical calculations and proofs; (2) avoid submitting sensitive personal data to any tutoring session; and (3) test the skill with a few sample problems to confirm its style and rigor meet your needs before relying on it for high-stakes work.
Review Dimensions
- Purpose & Capability
- okName/description (teach and solve math) match the SKILL.md guidance (teaching strategies for children, students, experts, teachers); nothing in the package asks for unrelated access.
- Instruction Scope
- okRuntime instructions are limited to pedagogical behavior and problem-solving guidance; they do not direct the agent to read files, access environment variables, or transmit data to external endpoints.
- Install Mechanism
- okNo install spec and no code files are present (instruction-only), so nothing will be written to disk or fetched at install time.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths — proportional and minimal for a tutoring skill.
- Persistence & Privilege
- okalways is false and the skill does not request system or cross-skill configuration changes; autonomous invocation is allowed by platform default but presents no additional risk here.