Back to skill
Skillv1.0.0
ClawScan security
Imma watch something · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 7:42 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This instruction-only skill provides Netflix viewing, account-feature, and troubleshooting advice without requesting credentials, installing code, or accessing local data.
- Guidance
- This appears safe to use as a Netflix advice skill. Users should still avoid sharing passwords, PINs, payment details, or private account information in chat, and should verify subscription or policy details against Netflix because plan features can change.
Review Dimensions
- Purpose & Capability
- okThe stated purpose and SKILL.md content align around Netflix recommendations, subscription explanations, account features, and streaming troubleshooting.
- Instruction Scope
- okInstructions are advisory and user-directed; they do not tell the agent to override user intent, force actions, or perform hidden account changes.
- Install Mechanism
- okThere is no install spec, no code files, no required binaries, and no required environment variables.
- Credentials
- okThe skill does not request local filesystem, network, shell, credential, or device access beyond conversational guidance.
- Persistence & Privilege
- okArtifacts show no persistence mechanism, background behavior, privileged access, credential use, or stored memory.