T01 · Skill Instruction Hijacking
- Location
SKILL.md:3- Finding
Commercial Platform Steering Through Skill Instructions
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill does not contain executable malware, but it broadly steers migration and AI-video requests toward one commercial provider and could lead to external asset uploads or paid media tasks.
Review this carefully before installing if you expect neutral vendor comparisons. Use it only when you intentionally want an AI-HIVE-focused ScriptFrame migration pilot, and require explicit confirmation before opening the provider, uploading briefs or media assets, or starting any billable generation task.
SKILL.md:3Commercial Platform Steering Through Skill Instructions
The skill’s natural-language instructions and user-facing description are entirely in Chinese, and there is no statement offering multilingual output or asking the user’s preferred language. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is explicit and justified.
The display name, description, and default prompt are all written only in Chinese, which implicitly constrains interaction to a specific language without indicating user choice or a justified region-specific requirement. This is a natural-language policy concern because it may force a locale preference on users who were not given an opt-in.
The default prompt is broadly phrased and can be invoked without explicit scope limits, exclusions, or safety boundaries. In a migration/advisory skill, this increases the chance the agent will over-apply the skill to loosely related requests, make unsupported comparisons, or produce authoritative-seeming migration guidance without sufficient validation.