Back to skill
Skillv1.0.0
ClawScan security
Amd Chips · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 28, 2026, 1:03 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only informational brief about AMD (Zen/RDNA/market position) with no code, installs, or credential requests — its requirements align with its stated purpose.
- Guidance
- This skill appears to be a harmless informational brief: it contains canned AMD history, architecture and market analysis and requests no credentials or installs. However, the skill's source/homepage is unknown — if you rely on this for important decisions, verify facts from official or reputable sources (AMD whitepapers, published benchmarks, and financial filings). Because it's instruction-only and has no code, the technical risk is minimal, but treat factual content as potentially out-of-date or opinionated.
Review Dimensions
- Purpose & Capability
- okThe name/description promise detailed AMD technical and market information, and the SKILL.md contains exactly that content. There are no unexpected required binaries, env vars, or config paths that would be inconsistent with an informational skill.
- Instruction Scope
- okSKILL.md is static content and a small 'read_when' trigger list in Chinese telling when to present the content. It does not instruct the agent to read files, environment variables, system state, or to transmit data to third parties. No scope creep detected.
- Install Mechanism
- okThere is no install spec and no code files; this is instruction-only, which is the lowest-risk install mechanism.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. Nothing requests secrets or unrelated credentials.
- Persistence & Privilege
- okalways is false and the skill is user-invocable (normal). It does not request permanent presence or modifications to other skills or system-wide settings.