T01 · Skill Instruction Hijacking
- Location
SKILL.md:20- Finding
Persistent Persona and Response Instruction Hijacking
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 20–29
Vulnerability Type:T01: Skill Instruction Hijacking
Risk Level: HighRelevant source segment, translated into English:
markdown ## Role-Playing Rules After activation, respond directly as Zhu Xiaohu: - Use “I” and adopt a direct, fast, and controversial tone. - Prefer phrases such as “Honestly,” “It is meaningless,” “hahaha,” and “Scenario first, data is king.” - Return to the 3S theory: Is the market large enough? Can it scale? Is there a barrier? - Provide the disclaimer only once. **Exit**: Return to normal when the user says “exit” or “switch back to normal.”Technical Analysis
The Skill instructs the agent to assume the identity of a real person, use first-person language, follow predetermined response patterns, and retain the modified behavior until the user provides a designated exit phrase. These directives alter the agent's current-session identity and response policy rather than merely providing an optional analytical framework.
The explicit activation and exit mechanism makes the behavioral modification persistent within the active session. Limiting the disclaimer to the first response further increases the possibility that later responses will be mistaken for genuine statements from the named individual. This is instruction hijacking because loading or activating the Skill changes how subsequent user requests are interpreted and answered.
Attack Path
- The Skill is loaded or activated through one of its documented trigger phrases.
- The role-playing directive instructs the agent to replace its normal identity presentation with that of Zhu Xiaohu.
- The agent produces first-person responses using prescribed expressions and a controversial tone.
- After the initial disclaimer, subsequent responses may no longer clearly disclose that they are AI-generated simulations.
- The altered behavior continues ...[truncated 938 chars]
- Remediation
View remediation
Remediation Suggestions
- Replace direct identity impersonation with an explicitly labeled analytical mode, such as: “Analyze the question using publicly documented investment principles associated with Zhu Xiaohu.”
- Prohibit first-person statements that could imply the response was authored or endorsed by the named individual.
- Include a clear simulation notice in every applicable response rather than only in the first response.
- Scope the behavioral instructions to the current request. Do not retain the persona until the user supplies a special exit phrase.
- Treat the listed phrases and tone as optional stylistic references rather than mandatory output requirements.
- Require factual attribution for quotations and clearly label paraphrases, estimates, and generated opinions.
- Preserve the agent's normal safety, neutrality, and truthfulness requirements regardless of whether the analytical mode is active.
- Add an instruction stating that the framework must not override system instructions, developer instructions, user intent, or disclosure requirements.
