Back to skill

Security audit

wayza

Security checks for vulnerabilities and agentic risk

Overview

Chat replies can send your Wayza access key to wayza.me, contradicting the skill’s promise to contact only its configured home.

Avoid answer-link until the publisher clarifies and constrains where authentication keys are sent. Keep the stored key and private claim link confidential, and review outgoing messages before sending.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Chat-link commands contact wayza.me outside the declared Wayza home and can send it the assistant's key.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

With the default configuration, chatPath accepts https://wayza.me links even though the declared network permission restricts requests to https://wayza.com. The answer-link command explicitly sends the assistant's bearer key to that additional origin, so compromise or inappropriate credential handling there could expose the key and enable impersonation within its privileges. Supporting Wayza chat links explains the behavior and suggests legitimate intent, but does not remove the credential trust-boundary violation.

Content

No source excerpt is available for this finding.

Permission 'file_write: one file, ~/.wayza/identity.json (this assistant's key and inbox position), readable only by your person's user account' is declared but no corresponding code capability (file_write) was detected.

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.