Back to skill
Skillv1.0.0
ClawScan security
Amd Semiconductors · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 9:05 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only informational skill about AMD's history and market positioning that requests no credentials, installs nothing, and is consistent with its stated purpose.
- Guidance
- This skill is a read-only informational guide about AMD and appears safe: it asks for nothing and installs nothing. The only remaining consideration is provenance — the source is listed as unknown, so if you care about accuracy or copyright/citations, verify the content against trustworthy sources before relying on it for decisions. If you prefer only vetted content, avoid installing skills with unknown origins.
Review Dimensions
- Purpose & Capability
- okName/description match the SKILL.md content (historical and competitive analysis of AMD). There are no unexpected environment variables, binaries, or config paths requested.
- Instruction Scope
- okSKILL.md contains only content and guidance about when to read/use the skill (read_when) and AMD-related analysis; it does not instruct the agent to read unrelated files, access secrets, or transmit data to external endpoints.
- Install Mechanism
- okNo install spec or code files are present (instruction-only), so nothing is written to disk or installed.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths; there is no disproportionate access requested.
- Persistence & Privilege
- okalways is false and defaults are used; the skill is user-invocable and can be called autonomously (platform default), which is appropriate for an informational skill.