T01 · Skill Instruction Hijacking
- Location
SKILL.md:31- Finding
Mandatory Persona Impersonation and Attribution Injection
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only persona and signing guide for Logos-branded thought-leadership content, with no code, persistence, credential use, or hidden runtime behavior.
Install this only if you want an agent to produce content in the Logos(诺声) persona and potentially include Logos attribution. For ordinary article, speech, or brand-copy requests, confirm whether you want Logos-branded signed output before publishing.
SKILL.md:31Mandatory Persona Impersonation and Attribution Injection
The skill is defined with a Chinese identity, naming, and output framing throughout, but does not state that users may choose another language or locale. Because the instructions consistently prescribe a single language/style context for generated public content, this can violate language/locale policy when user preference or deployment context differs.
The activation trigger is broad enough to match many ordinary writing requests such as external content creation, speeches, opinion pieces, and brand messaging. That can cause the agent to invoke this persona unexpectedly, overriding task-specific instructions or narrowing responses into branded signed output, which is a prompt-scope control issue even if not overtly malicious.