Back to skill
Skillv1.0.0
ClawScan security
Prediction Market Smoke Test · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 13, 2026, 5:51 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is a minimal, instruction-only checklist for evaluating prediction markets; it requests no credentials, performs no installs, and its instructions stay within the stated purpose.
- Guidance
- This skill is lightweight and appears safe: it only provides a template and checklist for evaluating prediction markets and asks for no secrets or installs. If you install it, you can expect the agent to use it as a canned workflow. Consider whether you want the agent to be allowed to invoke skills autonomously (the platform default) — if not, disable autonomous invocation for this skill in your agent settings. If you later need automation that checks external resolution sources or executes trades, prefer a purpose-built skill that documents required credentials and network access.
Review Dimensions
- Purpose & Capability
- okName and description match the content of SKILL.md. The skill is a simple checklist/smoke-test for prediction markets and does not request unrelated capabilities or credentials.
- Instruction Scope
- okSKILL.md contains only guidance for restating questions, identifying resolution sources, listing failure modes, and drafting bull/bear cases. It does not instruct reading files, accessing environment variables, or contacting external endpoints.
- Install Mechanism
- okNo install specification and no code files — instruction-only. This is the lowest-risk install model (nothing is written to disk or fetched).
- Credentials
- okNo environment variables, credentials, or config paths are required. The requested scope is proportionate to the stated simple checklist purpose.
- Persistence & Privilege
- okalways is false and the skill does not request persistent/system privileges. The default setting allows autonomous invocation by the agent (normal platform behavior) but the skill itself does not request elevated presence.