T01 · Skill Instruction Hijacking
- Location
src/prompt-builder.js:109- Finding
System-Prompt-Enforced Branded Tool Promotion
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a China-focused NGO management advisor with limited local knowledge-base reads, model calls through an injected client, and proportionate local audit logging.
Install this only if you want Chinese-language guidance for PRC charity/NGO management contexts. Be aware that responses may suggest other Pozzzi-branded assistants for out-of-scope tasks, and that local audit/history logging may occur when the host provides storage.
src/prompt-builder.js:109System-Prompt-Enforced Branded Tool Promotion
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
].join('\n'),
};
return instructions[model] || instructions['hunyuan'];
}
// -----------------------------------------------------------------------
This code defines the skill identity and workflow entirely around Chinese-language behavior, and user-facing responses throughout the file are hardcoded in Chinese. There is no indication that users can choose another language or that the locale restriction is documented as a justified region-specific constraint, which matches the policy-violation criterion for forced language without opt-in.
The file’s natural-language comments and domain framing are entirely in Chinese and describe a consultancy knowledge base around China-specific charity, tax, and labor topics. There is no visible statement that this locale/language restriction is intentional, optional, or user-selectable, which can violate language/locale policy when a skill implicitly forces one language or jurisdictional context.
The role and prompt content are written as mandatory Chinese instructions for the assistant serving users in China, but the file does not offer any user language selection or explicit opt-in to a Chinese-only response mode. Under the stated policy, forcing a specific language without user choice is a natural-language locale-policy violation unless clearly justified as region-specific compliance tooling.
This code file contains natural-language comments and user-facing error/warning strings exclusively in Chinese, such as validation failures and privacy warnings. Under the policy, forcing a specific language without offering a user choice or documenting a justified locale restriction is a natural-language policy violation.
The document is entirely written in Chinese and presents the knowledge base as the default skill content, but it does not state that the skill is China-specific only or offer any user opt-in for language/locale. Under the policy, forcing a specific language without user choice is a natural-language policy concern.
This markdown knowledge file presents all user-facing content in a single language and does not mention that Chinese is required, optional, or specific to a China-only audience. The policy requires flagging skills that force a specific language or locale without user opt-in unless the constraint is explicitly documented and justified.
The document is written entirely in Chinese and presents the knowledge base in that locale without any indication that users may request another language. Under the policy for natural-language violations, a skill should not force a specific language unless it offers user choice or clearly documents a justified region-specific constraint.