Security audit
Proxy: Creative Strategy and Ad Intelligence
Security checks for vulnerabilities and agentic risk
Overview
The skill provides a clearly disclosed competitor-ad research connection, with confirmation before sharing the company domain and consent before scheduling recurring work.
Connecting sends research queries and the confirmed company domain to Proxy. Review the OAuth permissions and credit costs, and enable weekly research only if wanted. Both scanners reported no findings; independent inspection resolved the reported local-reference gaps, but did not verify the hosted server's implementation.
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