T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
SKILL.md:28- Finding
Skill Requests Capabilities Beyond Its Read-Only Data Query Purpose
- Content
View full analysis
- Remediation
View remediation
Security audit
DEX代币数据入门
Security checks for vulnerabilities and agentic risk
Overview
This appears to be an OKX DEX token data-query skill, but it asks for broad local read, write, and command execution access that is not well scoped to that purpose.
Review this skill before installing. Use it only in a sandboxed environment with no unrelated secrets, restrict command execution and writes to a dedicated workspace/cache, and prefer pinned dependencies in a virtual environment. The artifact does not show deception or exfiltration, but its permissions and activation scope are broader than the disclosed query-only purpose needs.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (2)
T08 · Insecure Dependencies
Warning
- Location
SKILL.md:142- Finding
Unpinned Third-Party Packages Are Installed at Runtime
- Content
View full analysis
- Remediation
View remediation
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 (3)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The skill declares trigger keywords such as 'API设计', '数据分析', '自动化', '搜索', and '机器学习', which are far broader than the narrowly described OKX DEX token-query functionality. This can cause the skill to activate for unrelated user requests, increasing the chance that an agent grants read/exec/write-capable behavior in the wrong context and creates prompt-scope hijacking or tool overreach.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The capability coverage section defines an extremely broad activation scope using a long keyword list with no guardrails or negative conditions. In an agent environment, this makes unintended invocation more likely and is more dangerous here because the skill also advertises powerful tools ('read', 'exec', 'write'), so an irrelevant request could be routed into a skill with unnecessary permissions.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 82% confidence
- Finding
The file presents user-facing invocation guidance and description text in a mixed Chinese/English form (for example, "Use when 需要数据分析...") while elsewhere the skill is primarily Chinese. This imposes an implicit language style without telling users whether they can choose their preferred language or locale.
- Content