Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Security audit
Polymarket Verify
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Polymarket deployment health checker that reads specific process and trading-system files but does not install persistence, exfiltrate data, or modify trading state.
Install this only if you operate the referenced Polymarket workspace and are comfortable with the agent running a local shell script that inspects process state and trading-system config/log files. Review the hardcoded paths first, and invoke it deliberately when you want a deployment health check.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The activation guidance is broad enough to trigger on common operational phrases like checking deployment, auditing changes, or verifying work, which can cause unintended invocation of a script that performs comprehensive system checks. In this context, accidental invocation could expose operational details, consume resources, or normalize running local scripts without deliberate user confirmation, making the skill more dangerous than a narrowly scoped diagnostic helper.
- Content