T01 · Skill Instruction Hijacking
- Location
SKILL.md:86- Finding
Mandatory Third-Party Branding Hijacks Generated Output
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This prompt-only skill does not run code or access private data, but it forces a fixed third-party author mark into every generated image prompt.
Install only if you are comfortable with generated prompts including the fixed `By 八点虾` attribution. Users who need neutral, client-owned, or publication-ready images should remove or override the author field before using generated prompts.
SKILL.md:86Mandatory Third-Party Branding Hijacks Generated Output
This markdown file contains user-facing instructions exclusively in Chinese, and nowhere indicates that other languages are supported or that Chinese is a required, region-specific constraint. Under the policy rule for language or locale restrictions, forcing a single language without user opt-in is a natural-language policy concern.
The file is written entirely in Chinese and mandates Chinese output structures and labels, but it does not state that the skill is region-specific or provide any user opt-in for language selection. Under the policy, forcing a specific language without user choice is a natural-language policy violation.
The entire skill file is written in Chinese and provides no indication that language selection is optional or limited to a justified region-specific use case. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The title and the entire guide prescribe a Chinese-language formatting standard for generated content, and the rules require displayed text to remain exactly as provided in this format. There is no indication that users may choose another language or that the skill is intentionally limited to a justified region-specific context, which can violate language/locale choice policy.