Back to skill
Skillv1.0.0
ClawScan security
Medtronic · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 18, 2026, 7:04 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only, read-only informational skill about Medtronic; it does not request credentials, install software, or perform actions beyond presenting company facts.
- Guidance
- This skill is an informational summary about Medtronic and appears safe in terms of permissions and behavior. Note the source/homepage is unknown — treat the content as a static summary that may be outdated or incomplete, and verify critical medical or corporate information against official Medtronic sources before relying on it for decisions. No credentials or installs are required, so the privacy/credential risk is minimal.
Review Dimensions
- Purpose & Capability
- okName/description (Medtronic company information) matches the SKILL.md content, which is a factual summary and timeline; nothing requested or required is out of scope.
- Instruction Scope
- okSKILL.md only contains static company information and a small 'read_when' trigger list; it does not instruct the agent to read files, access env vars, call external endpoints, or transmit data.
- Install Mechanism
- okNo install spec, no downloads, and no code files — lowest-risk instruction-only skill.
- Credentials
- okNo environment variables, credentials, or config paths requested; nothing disproportionate to an informational skill.
- Persistence & Privilege
- okSkill is not always-enabled and uses normal invocation; it does not request persistent system privileges or modify other skills/config.