Back to skill
Skillv1.0.9

ClawScan security

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

Scanner verdict

BenignFeb 22, 2026, 7:36 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's code, declared requirements, and runtime instructions are coherent with its stated purpose (SmartBill invoicing) and do not request unrelated privileges.
Guidance
This skill appears to be what it says: a local Python CLI for SmartBill. Before installing or running it: 1) Only provide SMARTBILL_USERNAME/TOKEN to skills you trust; the source/homepage is unknown so verify the script contents yourself. 2) Use --dry-run to inspect normalized payloads and require explicit confirmation before issuing final invoices. 3) Do not enable SMARTBILL_DEBUG in production — it can log request/response bodies (sensitive). 4) When downloading PDFs, ensure --output is a safe path under your intended directory and that the script actually enforces no ../ traversal (review the script to confirm). 5) Prefer using short-lived or limited-scope tokens if SmartBill supports them. If you need higher assurance, ask the publisher for a verified source or code provenance (repo, release tags) before handing over real credentials.

Review Dimensions

Purpose & Capability
okName/description (SmartBill invoices) match the required binaries (python3), declared env vars (SMARTBILL_USERNAME, SMARTBILL_TOKEN, SMARTBILL_COMPANY_VAT_CODE) and the included CLI script. There are no unrelated credentials, binaries, or install steps that don't belong to an API client for SmartBill. Note: the skill's source/homepage is unknown which reduces provenance but does not create an internal inconsistency.
Instruction Scope
noteSKILL.md instructs the agent to run the included Python CLI for validation, dry-run, create, list series, and download PDFs — all within the invoicing scope. The doc warns about debug logging and output path restrictions. One operational caution: the CLI can print full request/response bodies to stderr when SMARTBILL_DEBUG is enabled (potentially exposing sensitive data), and the SKILL.md relies on an environment/platform-level restriction that output paths must stay within allowed media roots — verify the script actually enforces safe output path resolution to avoid path-traversal or writing files outside the intended directory.
Install Mechanism
okNo install spec; the skill is instruction-only with a bundled Python script. This is low-risk compared to remote downloads or package installs. The script uses only stdlib modules (urllib, json, base64), which is proportionate to an API client.
Credentials
okRequired env vars are limited to SmartBill credentials and a company VAT code; SMARTBILL_TOKEN is the primary credential. No unrelated secret variables are requested. The presence of SMARTBILL_DEBUG (optional) can cause sensitive request/response data to be logged to stderr — the SKILL.md documents this but users should avoid enabling it in production.
Persistence & Privilege
okThe skill is not always-enabled and does not request system-wide config or persistent privileges. It does write downloaded PDFs to disk (per user-supplied --output), which is appropriate for a CLI tool but should be constrained to safe paths (see instruction_scope note). Autonomous invocation is allowed by default but is normal for skills and not by itself a concern here.