T09 · Insecure Skill Coding Practices
- Location
SKILL.md:36- Finding
Shell Command Injection Through Unescaped User-Controlled Fields
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill has a clear knowledge-base purpose, but it writes persistent records to a fixed enterprise sheet and documents an unsafe shell-command pattern using user-controlled fields.
Review carefully before installing. Only use this skill with a known WeCom sheet you control or trust, confirm the destination before each write, and avoid executing the documented command through a shell with raw user-provided titles, URLs, categories, or summaries.
SKILL.md:36Shell Command Injection Through Unescaped User-Controlled Fields
The trigger conditions are broad enough that ordinary mentions of '知识库', generic requests to archive information, or simply sending a document link could invoke a workflow that writes data into a fixed enterprise smart sheet. In this skill, unintended invocation is more dangerous because the action is persistent and targets a specific shared repository, creating a risk of accidental data entry, privacy leakage, or unauthorized record creation.
The skill hardcodes a specific enterprise document ID, sheet ID, and table link, but does not prominently warn users that their provided titles, summaries, categories, and URLs will be written into that fixed shared destination. This can lead to silent exfiltration of potentially sensitive links or document descriptions into an organizational knowledge base, especially if users assume the assistant is only summarizing rather than persisting data.
The natural-language instructions and examples are entirely in Chinese and specify response phrasing in Chinese, but they do not state that the skill is intentionally limited to a Chinese-speaking or region-specific context. Under the policy, forcing a specific language without user opt-in can be a locale/language policy issue.