Back to skill
Skillv1.0.0
ClawScan security
Ads Landing Page Audit · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 6:22 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This instruction-only skill provides advertising audit guidance and does not request code execution, credentials, persistence, or direct account access.
- Guidance
- This appears safe to install as an advisory audit skill. Users should still avoid sharing unnecessary private business data, ad-account details, or owner contact information unless needed for the specific audit.
Review Dimensions
- Purpose & Capability
- okThe described purpose and SKILL.md content are coherent: it focuses on paid-traffic audit workflows, conversion blockers, spend risk, and structured mitigation guidance.
- Instruction Scope
- okThe skill asks the agent to produce summaries, findings, mitigation actions, ticket payloads, and checklists; it does not instruct the agent to directly change ad accounts or bypass user review.
- Install Mechanism
- okNo install spec, code files, required binaries, environment variables, or package dependencies are present.
- Credentials
- okThe skill has no declared need for local system access, network access, credentials, or privileged environment capabilities.
- Persistence & Privilege
- okThe artifacts do not request persistent storage, background execution, account credentials, tokens, browser sessions, or elevated privileges.