Back to skill
Skillv1.0.0
ClawScan security
math · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 16, 2026, 8:58 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only math tutoring helper whose requested resources and runtime instructions match its stated purpose and do not ask for credentials, installs, or unrelated access.
- Guidance
- This skill is internally consistent and appears safe: it's an instruction-only math tutor with no installs or credential requests. Keep in mind (1) the skill was published by an unknown owner with no homepage — that affects trust independent of technical coherence; (2) even coherent tutoring output can contain mistakes, so verify important results (especially for graded work or proofs); and (3) the platform allows autonomous invocation by default, so check agent settings if you do not want skills to run without explicit prompts.
Review Dimensions
- Purpose & Capability
- okName and description (math tutor/explorer) align with the SKILL.md pedagogy and problem-solving guidance; nothing requested (env, binaries, installs) is outside that purpose.
- Instruction Scope
- okSKILL.md contains pedagogical rules and problem-solving heuristics only; it does not instruct reading files, accessing environment variables, running commands, or calling external endpoints.
- Install Mechanism
- okNo install spec and no code files — instruction-only skill, so nothing is written to disk or downloaded during install.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths; nothing in the instructions implies hidden credential access.
- Persistence & Privilege
- okalways is false and the skill is user-invocable; it does not request persistent or elevated system presence.