Security audit
Openclaw Ai Marketing
Security checks for vulnerabilities and agentic risk
Overview
This markdown-only skill describes a disclosed AI marketing operating workflow with public posting and email-send activities that should be user-controlled but are coherent with its purpose.
Install only if you want an agent to help run a marketing operation that may publish social posts, publish blogs, and prepare or execute lifecycle sends. Configure account access carefully, keep private credentials and customer data out of reusable packaging, and require human approval where public posts or customer emails matter.
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