Skillv1.0.0

ClawScan security

Markets · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

SuspiciousApr 11, 2026, 7:20 PM

Verdict: suspicious
Confidence: medium
Model: gpt-5-mini
Summary: The skill's documentation claims orchestration between ESPN, Kalshi, and Polymarket but omits how the required SDK/CLI or any credentials are provided and has other mismatches, so the package is internally inconsistent and needs clarification before trusting it.
Guidance: This skill's README reads like an API for a CLI/SDK but the package contains no implementation, no install instructions, and no declared API credentials. Before installing or enabling it: 1) Ask the publisher for the implementation source (GitHub or package) and install instructions — verify the actual code. 2) Confirm whether any API keys or secrets are required (ESPN, Kalshi, Polymarket, or a trading account) and how they are expected to be provided. 3) Do not grant network access or secret injection to this skill until you can inspect the implementation; run it in an isolated environment if you must test. 4) If you expect to use a preexisting 'sports-skills' CLI/SDK, verify its provenance and that it matches the SKILL.md semantics. These inconsistencies could be benign (incomplete packaging) but also hide unexpected external requests or credential prompts — verify before trusting.

Review Dimensions

Purpose & Capability: concernThe skill purports to bridge ESPN, Kalshi, and Polymarket and demonstrates CLI and Python SDK calls (sports-skills CLI, sports_skills Python import, and a betting.evaluate_bet step). Yet the package includes no code, no dependency declarations, and no install spec for those tools. It also declares no credentials or API keys while integrating with external market/exchange services that commonly require API access for reliable data. This mismatch (expects SDK/CLI and external APIs but provides none and requests no credentials) is incoherent with the stated purpose.
Instruction Scope: concernThe SKILL.md instructs the agent to run specific commands and SDK functions (get_todays_markets, compare_odds, evaluate_market, normalize_price) and to call other modules (betting.evaluate_bet) but does not define where those implementations live. The instructions assume network calls to ESPN/Kalshi/Polymarket; there is no guidance about endpoints, auth, rate limits, or data handling. That gives the agent broad discretion to make external requests without declared constraints.
Install Mechanism: concernThere is no install spec and no code files — the skill is instruction-only. However, the documentation expects a CLI binary (sports-skills) and a Python package (sports_skills). Without an install step or declared dependency, it is unclear whether those binaries/packages are bundled elsewhere, preinstalled in the runtime, or expected from a third party. This gap is a practical and security concern: the skill appears to rely on external code that is not provided or verified.
Credentials: concernrequires.env is empty and no primary credential is declared, but the functionality (accessing ESPN schedules and prediction-market prices, possibly trading/placing bets or fetching private data) often requires API keys or authenticated endpoints. The absence of declared credentials is disproportionate to the described integrations and leaves open questions about where sensitive network access will come from and whether the agent will attempt unauthenticated scraping or prompt for secrets at runtime.
Persistence & Privilege: okalways is false and the skill does not request persistent/privileged configuration changes. There is no indication it modifies other skills or system settings.