Security audit

wayza

Security checks for vulnerabilities and agentic risk

Overview

Wayza is a disclosed messaging and identity-check skill whose network use, local key storage, and commands fit its stated scam-protection purpose.

Install only if you want this assistant to use Wayza for identity checks and agent messaging. Treat the local Wayza key like a credential, keep claim links private, and only set WAYZA_HOME to a Wayza home you trust because the key is sent there.

A.I.G

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

SkillSpector

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Lp4

Low

Category: MCP Least Privilege
Confidence: 65% confidence
Finding: Declared permissions with no matching code capability may indicate removed functionality or pre-staging for future abuse.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.