Back to skill

Security audit

MPAS Maintainer for multi-party approvals

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a clearly disclosed approval-review role, with safeguards for consequential decisions and persistent setup only when requested.

Configure this role only for an agent you intend to authorize as an approver, and limit its signer permissions to appropriate resources. Approval can trigger immediate execution. Remove the appended instruction preamble to undo the persistent role. SkillSpector reported partial coverage; this verdict relies on direct review of the complete artifact, and publisher provenance was not independently verified.

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