Back to skill
Skillv1.0.0
ClawScan security
Kodak Camera · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 28, 2026, 6:04 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only informational skill about Kodak's history; its declared requirements and runtime instructions are coherent with its stated purpose and it requests no credentials or installs.
- Guidance
- This skill appears internally consistent and low-risk: it only provides prewritten material about Kodak and asks for no credentials or installs. Before installing, consider whether you want third‑party authored content without source citations (SKILL.md contains no references); if factual accuracy or primary sources matter, verify the dates and claims independently. Also note that allowing the agent autonomous invocation is normal but means the skill could be used by the agent when relevant — there are no signs here that it will access or exfiltrate any data.
Review Dimensions
- Purpose & Capability
- okName/description (Kodak history, innovation failures) match the SKILL.md content. The skill does not request unrelated binaries, env vars, or config paths.
- Instruction Scope
- okSKILL.md contains only static, topical content and read_when triggers for when to present the material. It does not instruct the agent to run commands, read files, access environment variables, or transmit data to external endpoints.
- Install Mechanism
- okNo install spec and no code files — lowest-risk, instruction-only skill; nothing is written to disk or downloaded.
- Credentials
- okThe skill requires no environment variables, credentials, or config paths — proportionate to an informational/history skill.
- Persistence & Privilege
- okalways is false and normal model invocation is allowed; this is standard for skills and does not request elevated or permanent privileges.