T09 · Insecure Skill Coding Practices
- Location
templates/compress.py:120- Finding
Destructive Cleanup of an Unvalidated Existing Destination Directory
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This comic-making skill is mostly coherent, but its bundled compression script can delete unrelated files if pointed at an existing destination folder.
Review before installing. Use the compression script only with a newly created, dedicated output folder such as comic_publish, avoid pointing it at a project root or documents folder, and escape or sanitize story text before publishing generated HTML from untrusted input. Expect the default workflow and template to be Chinese-language oriented and to load Google Fonts unless modified.
templates/compress.py:120Destructive Cleanup of an Unvalidated Existing Destination Directory
templates/comic_template.html:284Generated Comic Content Is Inserted into HTML Without an Escaping Requirement
[结尾文字]
templates/comic_template.html:8Comic Template Makes an Undeclared Runtime Request to Google Fonts
Without declared permissions the skill's intent is opaque and cannot be validated.
The manifest description is written as producing comics from text content and explicitly targets Chinese trigger phrases such as “把我的故事做成漫画” and “生成连环画,” while the workflow later hard-codes Chinese text artifacts like 剧本.md and Chinese dialogue limits. This indicates a language-specific constraint without user opt-in or a documented regional/compliance justification, which matches the language/locale policy violation criteria.
The workflow requires output as 剧本.md with Chinese-labeled fields such as 对白, 心理活动, and 旁白, and later sections continue to prescribe Chinese text handling rules. Because the file does not present this as an optional locale mode or ask the user to choose language, it imposes a specific language convention by default.
The trigger phrases are broad consumer-style requests such as '把我的故事做成漫画' and '故事转漫画', which are likely to match ordinary user intents outside a narrowly scoped invocation. This can cause the skill to activate unexpectedly and gain access to powerful tools like ImageGen and Bash in contexts where the user did not clearly intend to invoke this workflow, increasing the risk of overreach or unintended tool use.
The HTML root element hard-codes lang="zh-CN", which enforces a specific language/locale in the template. There is no accompanying note that this is optional, user-selected, or justified as a region-specific template, so it appears to violate the locale-choice policy.