T09 · Insecure Skill Coding Practices
Error
- Location
SKILL.md:30- Finding
Automatic Paid Requests Use a High-Impact Wallet Private Key Without Explicit Authorization Controls
- Content
View full analysis
- Remediation
View remediation
Security audit
Ai Narrative
Security checks for vulnerabilities and agentic risk
Overview
The skill is a disclosed paid market-signal integration, but it asks agents to use a raw EVM private key for automatic wallet-funded requests without clear spending controls or per-call user confirmation.
Install only with a dedicated low-balance wallet, confirm the expected price before use, and avoid enabling unattended or repeated invocations unless you have external spending limits and key-rotation procedures in place.
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
- 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 (1)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill instructs the agent to make an x402-authenticated request using the user's EVM private key and states that payment authorization is handled automatically, but it does not present a prominent warning that each invocation can spend wallet funds. In an agent setting, this can lead to unintentional paid calls, repeated charges, or abuse through looping/trigger-happy automation because the wallet-backed payment side effect is not clearly disclosed where usage is described.
- Content