Security audit
Gws Modelarmor Sanitize Prompt
Security checks for vulnerabilities and agentic risk
Overview
This skill is a straightforward Google Model Armor CLI wrapper that sanitizes prompt text using a user-specified template.
Install only if you intend to use the `gws` CLI with Google Model Armor and are comfortable sending the selected prompt text or JSON to the configured Google Cloud template. Review the shared `gws` auth/global settings in your environment because this artifact depends on them but does not include them.
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.