Back to skill
Skillv1.0.0
ClawScan security
Mma · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 16, 2026, 9:31 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is a coherent, instruction-only skill that provides static MMA/UFC information, requests no permissions or installs, and does not perform any external operations.
- Guidance
- This skill appears safe and internally consistent: it only serves static MMA/UFC information and requires no permissions or installs. Note that the source/homepage is missing and content may become outdated or contain factual errors; if you need live scores or authoritative data, prefer an official or well-maintained data source (e.g., UFC website or a verified sports API). If you have concerns about provenance, only enable it when needed and validate important facts separately.
Review Dimensions
- Purpose & Capability
- okThe name, description, and SKILL.md all describe MMA/UFC rules, history, fighters, and event info — the requested capabilities and content align with the stated purpose.
- Instruction Scope
- okSKILL.md contains static informational content and simple read_when triggers; it does not instruct the agent to read files, access environment variables, call external endpoints, or perform other actions outside the skill's scope.
- Install Mechanism
- okThere is no install spec and no code files. As an instruction-only skill, nothing is written to disk or installed at runtime.
- Credentials
- okThe skill declares no environment variables, credentials, or config paths — which is appropriate for a read-only informational skill.
- Persistence & Privilege
- okThe skill does not request always-on presence and uses default invocation settings; it does not modify other skills or system-wide configuration.