T09 · Insecure Skill Coding Practices
Note
- Location
scripts/build_url.py:35- Finding
Unencoded Category Parameter Allows Query-String Injection
- Content
View full analysis
- Remediation
View remediation
Security audit
Alibaba Ai Search
Security checks for vulnerabilities and agentic risk
Overview
This skill is a simple Alibaba search URL helper with disclosed attribution tracking and no evidence of hidden, persistent, or destructive behavior.
Before installing, be aware that generated Alibaba links include traffic_type=ags_llm for analytics/attribution. Avoid using untrusted category values with the helper script until category URL encoding or validation is fixed.
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
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- 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 (1)
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The README explicitly states that all generated URLs include a tracking parameter for analytics and attribution, but it does not warn users about the privacy implications or give them a way to opt out. This is a real transparency/privacy issue because users may unknowingly share attribution metadata when following or distributing generated links, even though the parameter appears low risk and not overtly malicious in this context.
- Content