Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward document-extraction prompt for invoices, receipts, and contracts, with no bundled code or hidden execution behavior.
Install only if you are comfortable letting the agent read the specific invoices, receipts, contracts, images, or directories you provide. For best control, invoke it with explicit file paths and avoid broad directories unless you intend batch processing.
The natural-language instructions, workflow, outputs, and examples are all written as if the skill operates in Chinese, while the file does not state that language behavior is optional or user-selectable. Under the policy, locale or language constraints should not be imposed without opt-in unless clearly justified.
The trigger conditions are broad enough to activate on ordinary mentions of invoices, receipts, contracts, or extraction-related words, not just explicit user requests to run the skill. In an agent environment, this can cause unintended processing of sensitive financial or legal documents, increasing the risk of over-collection, privacy exposure, and surprising tool use.
