Clawhub Package Full
Analysis
This does not look like malware, but it gives an AI broad, credentialed control over an Odoo business system without clear approval or scoping guardrails.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
def execute(self, model: str, method: str, *args: Any, **kwargs: Any) ... def create(self, model: str, values: dict) ... def write(...) ... def unlink(...)
The client exposes generic Odoo RPC execution plus create, update, and delete operations. For an ERP connector this is purpose-aligned, but it is broad mutation authority and the artifacts do not show approval gates or scoped safeguards.
All operations use **smart actions** that handle fuzzy matching and auto-creation workflows.
Fuzzy matching and auto-creation can be useful, but in an ERP system a wrong match or auto-created customer/product/order can propagate into sales, inventory, invoices, HR, or ecommerce workflows.
Source: unknown; Homepage: none; No install spec — this is an instruction-only skill.
The package includes substantial Python source code, but the registry metadata does not provide a verified source or install contract. SKILL.md lists a GitHub repository, which users should verify.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
if not self.api_key: errors.append("ODOO_API_KEY is required ...") ... username=os.environ.get("ODOO_USERNAME" ... api_key=os.environ.get("ODOO_API_KEY"The code requires credentialed Odoo account access, while the registry metadata declares no required environment variables and no primary credential. That under-declares the privilege boundary users are granting.