Back to skill
Skillv1.0.0
ClawScan security
Global Ads Helper · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 4, 2026, 8:17 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only planner for global paid-media strategy and does not request credentials, install software, or instruct the agent to access unrelated system resources — its declared purpose matches its runtime instructions.
- Guidance
- This skill is internally consistent and low-risk as provided: it only offers planning logic and examples and doesn't request credentials or install code. Before using it in production, consider: (1) if you want the agent to execute live operations (push budgets, query ad accounts), you'll need to provide platform API credentials — validate any future version that adds API calls; (2) review generated recommendations for compliance with country-specific ad policies and privacy rules (the skill notes to flag policy differences but cannot enforce legal compliance); (3) monitor for any later updates that add network calls or install steps, since those would change the risk profile.
Review Dimensions
- Purpose & Capability
- okName/description (global ads planning across major ad platforms) align with the SKILL.md: it provides scoring, allocation, ROI forecasting and rollout guidance. The skill does not request platform API keys or unrelated capabilities, which is coherent for a strategy-only helper.
- Instruction Scope
- okSKILL.md contains purely high-level workflows, decision rules, input/output contracts and examples. It does not instruct the agent to read local files, access environment variables, call external endpoints, or exfiltrate data beyond producing planning outputs.
- Install Mechanism
- okNo install spec and no code files — instruction-only skill. Nothing will be written to disk or downloaded, which is low risk and consistent with the described behavior.
- Credentials
- okThe skill requires no environment variables, credentials, or config paths. For a planning/strategy skill this is proportionate; it does not request unrelated secrets or broad access.
- Persistence & Privilege
- okalways is false and model invocation is allowed (platform default). The skill does not request permanent system presence or attempt to modify other skills or system-wide settings.