Back to skill

Security audit

macro-sentinel-pro

Security checks for vulnerabilities and agentic risk

Overview

The skill’s economic monitoring, scheduled reports, and notifications fit its stated purpose, with no harmful behavior found in the supplied artifact.

Choose schedules, recipients, and callback destinations before enabling automation, and use narrowly scoped integration credentials. Keep financial integrations limited to alerts unless transaction authority is separately intended. The full scanner report reports complete coverage of the sole artifact, which was independently inspected; external integrations and sandbox enforcement remain unverified.

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