Incomplete referenced artifact analysis
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 先完整读取 [流程开发标准](references/workflow-standard.md)，查询 `cli workflow schema steps`、
Security audit
屏幕自动化工程师
Security checks for vulnerabilities and agentic risk
Overview
The skill’s desktop automation powers are clearly disclosed and include meaningful controls for sensitive data, risky actions, and stopping workflows.
Review generated steps and supervise the first run. Install only trusted workflows: Python extensions can access your files, network, and programs. Managed browser profiles retain logins. Confirm what screenshots may reach an external provider, and complete credentials and high-risk actions yourself.
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
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)
Static analysis
No suspicious patterns detected.