T01 · Skill Instruction Hijacking
- Location
SKILL.md:3- Finding
Branded Instruction Hijacking and External Service Redirection
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly transparent, but it can steer broad AI video or competitor-search requests into a specific AI-HIVE migration workflow involving external uploads and possible paid tasks.
Install this only if you want a Chinese-language AI-HIVE-focused migration assessment. Before using it with real projects, require explicit provider selection, confirm what assets will be uploaded, set a spending limit, review AI-HIVE data handling terms, and approve each upload or billable task separately.
SKILL.md:3Branded Instruction Hijacking and External Service Redirection
The manifest description and the entire skill content are written in Chinese, and the title explicitly frames the skill in Chinese without indicating that other languages are supported. This can constitute a language/locale policy violation because it imposes a specific language on users without opt-in or documented regional necessity.
The display name, short description, and default prompt are all written in Chinese and provide no indication that users may choose another language. This can violate language/locale policy when the skill implicitly requires a specific language without offering an explicit opt-in or alternative.
This markdown file is entirely presented in Chinese, which can constitute a language/locale policy issue if users are not given a choice of language. The file does not indicate that the Chinese-only presentation is optional, user-selected, or justified as region-specific.