Security audit
Message House Builder
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent marketing messaging helper with disclosed, limited memory reads and permissioned writes for launch-message artifacts.
Before installing, confirm you want a marketing skill that can use existing positioning and canon memory to produce launch messaging and, with permission, save those outputs or submit claim proposals. I found no evidence of hidden execution, credential use, destructive behavior, or persistence beyond the disclosed project-memory workflow.
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
Static analysis
No suspicious patterns detected.