Security audit
google-business-profile
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed Google Business Profile integration with high-impact business-listing powers, but its instructions are coherent and require user approval for writes, connections, automation, and credential-sensitive paths.
Before installing, understand that this skill can change public Google Search and Maps business listings, publish posts/photos, reply to reviews, delete listing content, and create persistent Maton functions or triggers. Use read/list operations first, confirm every write with the exact location and value, avoid raw API keys unless the CLI cannot be used, and review/delete any functions, triggers, or destinations when no longer needed.
- 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
- 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
Static analysis
No suspicious patterns detected.