Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md > 头像：`assets/avatar.png`
Security audit
裁判者办案指引
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed Chinese-language legal adjudication study/workbench guide with no commands, credential use, persistence, or hidden execution behavior.
Install only if you need Chinese-language civil/commercial adjudication or legal-methodology support. It should not replace current law, jurisdiction-specific rules, professional judgment, or formal legal authority, especially for users who are not judges, arbitrators, or legal professionals.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md > 头像：`assets/avatar.png`
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The activation rules are broad enough to trigger on generic legal-study or procedural terms, not just real adjudicator workflows. In a high-stakes legal domain, unintended invocation can cause the agent to adopt a judge/arbitrator framing for users who are not authorized decision-makers, increasing the risk of inappropriate quasi-judicial guidance or role confusion.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 82% confidence
- Finding
The document title and all operating guidance are written in Chinese, and the skill does not indicate that language selection is optional or that the material is intentionally limited to Chinese-speaking users. Under the policy rule for language/locale, a file can be flagged when it effectively enforces one language without user opt-in or an explicit justification.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The document is explicitly labeled for judges only ('法官专用版') without any access gating, audience validation, or alternative routing for non-judge users. In a broader agent environment, this can cause policy misuse or inappropriate delivery of specialized legal-process guidance to unauthorized or unintended audiences, even though the content itself is not overtly malicious.
- Content