Back to skill
Skillv1.1.0
ClawScan security
Pyx Scan · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 14, 2026, 1:40 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is internally consistent: it only fetches a remote PYX Scanner report for a given owner/name and formats that result; it does not request credentials, install code, or access local files.
- Guidance
- This skill simply asks the PYX Scanner service (https://scanner.pyxmate.com) about a skill identified as owner/name and formats the returned report. Before installing or relying on this skill, consider: 1) Do you trust the external PYX Scanner service and its privacy practices? The skill will make outbound requests to that domain for every check. 2) Avoid using it to scan private/internal skills if you don't want to share their owner/name with an external service. 3) The runtime has permission to run curl/WebFetch — if you prefer tighter controls, restrict network access or require explicit user confirmation before each check. 4) If the scanner returns UNSCANNED, CAUTION, or FAILED, follow your normal manual review processes (review source code, audit permissions) rather than relying solely on the automated verdict. The minor instruction inconsistency (fetch raw JSON vs. 'no raw JSON' reporting rule) is benign but you may want the skill author to clarify that the agent should fetch JSON then format it for users.
Review Dimensions
- Purpose & Capability
- okThe skill's name and description match its behavior: it queries an external PYX Scanner API for a skill's safety data and formats the response. It does not request unrelated credentials, binaries, or system access.
- Instruction Scope
- noteRuntime instructions stay within the stated purpose (call the remote scanner and produce a formatted report). Minor inconsistency: Step 2's WebFetch prompt asks for the raw JSON 'exactly as-is', while Behavioral Rule #5 requires formatted markdown rather than raw JSON. This is explainable (fetch raw JSON, then format it locally) but worth noting. The skill does not instruct the agent to read local files or environment variables nor to transmit anything beyond the API request for owner/name.
- Install Mechanism
- okNo install spec and no code files — instruction-only skill. This is lowest-risk from an install perspective.
- Credentials
- okNo environment variables, credentials, or config paths are requested. The single external dependency is the PYX Scanner API endpoint, which is proportional to the claimed purpose.
- Persistence & Privilege
- okThe skill is not always-enabled and does not request elevated or persistent privileges. It does not modify other skills' configs or require ongoing presence.