Security audit
Dust Language Architect
Security checks for vulnerabilities and agentic risk
Overview
This is an instruction-only Dust language helper that asks the agent to read Dust repository files broadly, with no hidden execution, credential use, or persistence.
Before installing, make sure the Dust repositories used with this skill do not contain secrets or unrelated private files, because the skill intentionally directs the agent to consider all files in those repositories. Otherwise, the behavior is disclosed, purpose-aligned, and proportionate.
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.