Skillv1.0.0

ClawScan security

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

Scanner verdict

BenignMar 7, 2026, 10:40 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill is internally consistent: it describes a hosted page-deployment API and only needs a Sutrena API key to operate; there are no surprising installs or unrelated credential requests, but it will send user content to sutrena.com so you should trust that external service before publishing sensitive data.
Guidance: This skill will make HTTP requests to sutrena.com and publish whatever HTML/forms/data you provide to a public subdomain — that is the intended function. Before installing or enabling it: 1) Only set SUTRENA_API_KEY if you trust sutrena.com, because a permanent key gives the skill ongoing publishing ability; otherwise let the agent use the ephemeral trial key flow (24h). 2) Do not include secrets, passwords, or sensitive personal data in content you ask the skill to publish. 3) Remember the agent is instructed to execute requests itself and return live URLs, so actions you request will create public pages; test with non-sensitive dummy content first. 4) If you prefer to keep control of network traffic, ask the agent to show curl commands so you can run them yourself rather than having the agent perform the requests. 5) The skill metadata has a small inconsistency (requires:{} vs primaryEnv set) and the registry source/homepage fields are sparse — if you need stronger assurance, verify the sutrena.com service and privacy/retention policy before use.

Review Dimensions

Purpose & Capability: okName/description (deploy pages/forms/dashboards) matches the instructions (POST JSON to sutrena.com endpoints). The only credential referenced is SUTRENA_API_KEY which is appropriate for a hosted API. Minor metadata inconsistency: requires:{} in the embedded metadata but primaryEnv is set to SUTRENA_API_KEY.
Instruction Scope: okSKILL.md explicitly instructs the agent to perform HTTP requests to sutrena.com, create pages/forms/dashboards, and return live URLs. The instructions do not ask the agent to read unrelated files or other environment variables. They do, however, require transmitting user-provided HTML/data to an external service (sutrena.com) — expected for this skill but important to note for privacy.
Install Mechanism: okInstruction-only skill with no install spec and no code files. Lowest installation risk — nothing is written to disk by the skill itself.
Credentials: noteThe only declared sensitive item is SUTRENA_API_KEY (primary credential), which is proportionate to the stated functionality. Note: the registry metadata shows no required env vars but the primaryEnv is SUTRENA_API_KEY — a minor inconsistency. If you set SUTRENA_API_KEY, the skill will use that permanent key rather than obtaining a short-lived trial key.
Persistence & Privilege: okalways:false and the skill is user-invocable; it does not request persistent platform-wide privileges or modify other skills. Autonomous invocation is allowed (platform default) but not combined with any elevated privileges here.