Security audit
Exa Neural Query Planner
Security checks for vulnerabilities and agentic risk
Overview
No malicious or suspicious signal was provided, and the available telemetry is clean, but the skill artifact itself was not present in the workspace for deeper verification.
This looks safe based on the supplied clean scan results, but because the actual skill files were not available for inspection here, review the skill's visible instructions and install steps before enabling it, especially for any requests involving credentials, local files, network services, or background tasks.
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.