Skillv1.2.2

ClawScan security

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

Scanner verdict

BenignMar 3, 2026, 6:06 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: Internally consistent instruction-only skill that issues curl requests to the Outtake Trust API and only requires a single OUTTAKE_API_KEY; nothing in the files or instructions asks for unrelated credentials or system access.
Guidance: This skill is coherent with its stated purpose: it sends URLs to Outtake's trust API using your OUTTAKE_API_KEY. Before installing, confirm you trust Outtake (app.outtake.ai) because every URL you check will be transmitted to that third party and may be logged. Do not submit URLs that contain sensitive tokens or credentials. Store the OUTTAKE_API_KEY securely (use a dedicated key for this agent if possible) and be mindful of the documented rate limits and any privacy/policy terms on Outtake. If you need offline or private scanning, this skill is not suitable because it relies on an external service.

Review Dimensions

Purpose & Capability: okThe name/description (URL safety / domain reputation) align with the declared requirements: curl and OUTTAKE_API_KEY. All endpoints referenced are under app.outtake.ai and the included reference doc documents the same API surfaces. No unrelated services, binaries, or config paths are requested.
Instruction Scope: okSKILL.md contains concrete curl examples for single and batch checks and a small registration flow to obtain OUTTAKE_API_KEY. It does not instruct the agent to read arbitrary files, credentials, or other environment variables, nor does it direct data to endpoints outside Outtake. Note: URLs (which may contain sensitive tokens) are sent to the third‑party Outtake API as intended by the skill.
Install Mechanism: okNo install spec or code to download — the skill is instruction-only and relies on existing curl being present. This is the lowest-risk install model and matches the declared required binary.
Credentials: okOnly a single API credential (OUTTAKE_API_KEY) is required and is justified by the documented Bearer auth. No unrelated secrets, keys, or config paths are requested. The SKILL.md uses that same environment variable and does not reference other undeclared env vars.
Persistence & Privilege: okalways is false (not force-included) and model invocation is allowed (platform default). The skill does not request persistent system changes, does not modify other skills, and does not require elevated privileges. Autonomous invocation is normal and not by itself a concern here.