Back to skill
Skillv1.0.0

ClawScan security

One API key for real time stock equity pricing data including crypto BTC ETH etc. · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignFeb 11, 2026, 9:08 AM
Verdict
Benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's requirements, instructions, and included client code are consistent with a market-data API client that needs a single AISA_API_KEY and standard network tools.
Guidance
This skill appears internally consistent with a market-data client. Before installing, confirm you trust the AIsa provider (api.aisa.one) and the source of your AISA_API_KEY. Use a key with minimal scope and monitor usage/quotas; avoid putting high-privilege or long-lived credentials into third-party skills without verifying the provider and their privacy/retention policies. If you need higher assurance, review the provider's documentation, TLS certs for api.aisa.one, and consider testing with a limited/staging API key first.

Review Dimensions

Purpose & Capability
okName/description claim real-time & historical market data; the skill asks only for curl/python3 and AISA_API_KEY and targets api.aisa.one endpoints. The single API key and requested binaries are appropriate and expected for this purpose.
Instruction Scope
okSKILL.md contains concrete curl examples and CLI usage for market data endpoints. Instructions reference only the AISA_API_KEY env var and the documented API endpoints; they do not request unrelated files, system state, or extra secrets.
Install Mechanism
okNo install spec (instruction-only) and included Python client script — nothing is downloaded from arbitrary URLs or written to unusual locations. Requiring python3/curl is proportionate and low risk.
Credentials
okOnly AISA_API_KEY is required (declared as primaryEnv). No unrelated credentials, config paths, or broad-scoped secrets are requested. The skill's code reads that env var and uses it as a bearer token — expected behavior.
Persistence & Privilege
okalways:false (not force-included). disable-model-invocation is false (normal); autonomous invocation is allowed but not excessive here. The skill does not attempt to modify other skills or system-wide configs.