Back to skill
Skillv1.0.0

ClawScan security

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

Scanner verdict

SuspiciousFeb 24, 2026, 8:35 AM
Verdict
suspicious
Confidence
medium
Model
gpt-5-mini
Summary
The skill's documentation describes powerful billing/admin API operations that require secrets (master/install/admin keys), but the skill metadata declares no required credentials or install steps and the source/homepage is unknown — this mismatch is concerning.
Guidance
This skill appears to be thorough API documentation for OfficeX and expects powerful secrets (master/install/admin keys) to perform billing and payouts, but it does not declare any required credentials or provide a verifiable source. Before installing: (1) treat it as suspicious until you verify the publisher and an official homepage; (2) do not supply high-privilege secrets (master/admin) unless you control them and the skill explicitly documents least-privilege usage; (3) prefer testing only against the staging endpoints with ephemeral or reduced-privilege keys; (4) require explicit prompts or operator confirmation before any reserve/settle/payout/admin operation; (5) ask the publisher to update metadata to declare required env vars and a primary credential and to provide a canonical homepage/source — that change would increase confidence. If you cannot verify the source, avoid giving this skill any production billing or admin credentials.

Review Dimensions

Purpose & Capability
noteThe name/description match the SKILL.md: this is a full OfficeX API integration (catalog, installs, billing, payouts, webhooks, admin). That capability legitimately requires API credentials and careful permissioning. However, the registry metadata declares no primary credential and no required environment variables despite the documentation explicitly referencing Master Key, Install Secret, and Admin Secret headers. The lack of declared credential requirements is disproportionate to the documented capabilities.
Instruction Scope
noteSKILL.md is comprehensive and stays focused on OfficeX APIs and endpoints (staging/production domains are documented). It describes actions with billing impact (reserve/settle/payout), install secret rotation, admin endpoints, and webhook handling. It does not appear to instruct reading unrelated local files or calling non-OfficeX endpoints, but it does direct use of highly sensitive operations (admin-level endpoints, payouts) which expand the risk surface if credentials are provided.
Install Mechanism
okNo install spec and no code files — lowest installer risk. This is instruction-only, so nothing will be written to disk by an installer. However, being instruction-only means the SKILL.md is the runtime authority, so missing metadata (especially about credentials) becomes the main concern.
Credentials
concernHigh concern: the docs require Master Key, Install Secret, and Admin Secret for many operations, but the skill metadata lists no required environment variables or primary credential. That omission is incoherent: a billing/admin skill should declare the credentials it needs and which one is primary. Asking for or using high-privilege secrets without declaring them increases the risk that secrets will be mishandled or unexpectedly requested at runtime.
Persistence & Privilege
okalways is false and disabling model invocation is false (normal). The skill does not request permanent presence or claim it will modify other skills. Autonomous invocation combined with admin/billing capabilities would raise risk, but on its own the persistence settings are standard.