T09 · Insecure Skill Coding Practices
- Location
scripts/upsell.py:47- Finding
Plaintext Customer Commercial and Operational Data Bundled with the Skill
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent local upsell-analysis tool, but it bundles and persists real-named customer-like commercial records in plaintext without clear provenance or controls.
Review the bundled customer data before installing. If these records are real or derived from real customers, they should be removed or replaced with clearly fictional examples, and runtime data should have documented retention, deletion, and file-permission controls.
scripts/upsell.py:47Plaintext Customer Commercial and Operational Data Bundled with the Skill
Without declared permissions the skill's intent is opaque and cannot be validated.
The trigger phrases include broad business terms such as 'upsell', '交叉销售', and '客户增长', which could activate the skill during ordinary conversations unrelated to intentional skill use. Overbroad activation increases the chance of unintended context capture, surprising behavior, or unsolicited business analysis based on user content.
The script automatically creates a local data directory under the user's home folder and writes customer and sales-signal data to JSON files without notice, consent, or any data-handling controls. Because the stored content includes identifiable customer names, spending, team size, and business activity signals, this can expose sensitive commercial information to other local users, backups, or endpoint monitoring systems.
All user-facing description and usage guidance are written in Chinese, and the file does not state that other languages are supported or that Chinese is an intentional opt-in locale. Under the stated policy, forcing a specific language without user choice can be a natural-language policy concern unless clearly documented and justified.
This JSON data includes multiple natural-language string values exclusively in Chinese, such as client names at L03, L09, L15, and L21, without any indication that the skill is region-specific or that users can opt into this locale. Under the policy for natural-language issues, fixed locale-specific content can be a violation when no choice or justification is provided.
The docstring and user-facing CLI descriptions/output are written in Chinese, which imposes a specific language/locale without any opt-in or alternative. The policy calls for flagging language or locale constraints unless the skill offers user choice or clearly documents a justified region-specific limitation.