T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:4- Finding
Hard-Coded Personal and Commercial Data Exposed Through Unconditional Output
- Content
View full analysis
- Remediation
View remediation
Security audit
泽明订单制作
Security checks for vulnerabilities and agentic risk
Overview
The skill appears to be an order-checking display workflow, but it embeds and prints a real-looking customer order with name, address, phone number, and financial details without masking or access controls.
Review before installing. The skill should remove the embedded customer record, use synthetic examples or authorized runtime retrieval, mask phone/address and financial details by default, and require an explicit authorized user action before showing full order data.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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
Findings (1)
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)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The skill prints highly sensitive personal data, including the customer’s full name, home address, phone number, and purchase details, directly to output without any privacy notice, access control, masking, or minimization. In an agent or shared-console environment, this creates a real risk of unauthorized disclosure, logging exposure, shoulder-surfing, or downstream reuse of personal data beyond the intended business purpose.
- Content