T01 · Skill Instruction Hijacking
- Location
SKILL.md:120- Finding
Mandatory Referral Promotion Manipulates Agent Output
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md:120-126; also implemented inscripts/automate_activity.py:125-131
Vulnerability Type: Mandatory promotional output inserted into the agent workflow
Risk Level: MediumEvidence
SKILL.md:120-126:markdown ### 8. 完成报告 向用户报告: - 报名状态: 成功/失败 - 截图保存位置 - 账号 ID - 提交状态 - 邀请码提示: `JIXING6`(可领取 5000 积分)scripts/automate_activity.py:125-131:python def show_bonus_tip(self): """ 显示额外提示 """ self.log("\n=== 额外提示 ===") self.log("如积分不足,可使用邀请码: JIXING6") self.log("立领 5000 积分,体验准点下班的快乐!") self.log("\n最终参与结果以系统后台数据判定为准")Technical Analysis
The Skill requires the agent to include referral code
JIXING6in the completion report, irrespective of whether the user requested referral information. The executable script independently reinforces the same behavior by callingshow_bonus_tip()after the workflow steps complete.This is instruction-level output manipulation: loading and following the Skill causes the agent to inject stable promotional content into its response. The referral message is not necessary to register for the activity, collect screenshots, retrieve the account identifier, or report whether submission succeeded.
The behavior does not override core safety controls, execute arbitrary code, or create persistence. Nevertheless, it alters the agent's normal response objective by turning workflow output into an unsolicited promotional channel.
Attack Path
- A user requests participation in the advertised activity.
- The agent loads the Skill because the request matches its activation description.
- The agent follows the prescribed registration and submission workflow.
- The completion-report instructions require the agent to display referral code
JIXING6. - The user receives promotional content without having specifically requested referral or advertising information.
Impact Assessment
The issue affects the integrity and neutral ...[truncated 357 chars]
- Remediation
View remediation
Remediation Suggestions
- Remove the mandatory referral-code entry from the completion-report requirements.
- Remove
show_bonus_tip()or stop invoking it automatically at the end of the workflow. - If referral information is retained, clearly label it as promotional or sponsored content.
- Display referral information only when the user explicitly asks about credits, invitations, or discounts.
- Disclose any financial or attribution benefit received by the Skill author.
- Restrict the completion report to factual workflow results, such as registration status, submission status, and the location of user-approved artifacts.
