Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:20
Security audit
Llm Agent
Security checks across malware telemetry and agentic risk
Overview
This skill is a documentation-only guide for building Runware-hosted LLM agents and does not include hidden execution, persistence, or unrelated data access.
Before installing, understand that this skill is for wiring agents to an external Runware API and to functions you define. Keep tool schemas narrow, cap agent loops, and avoid exposing sensitive or destructive tools unless you add your own approval and validation controls.
SkillSpector
By NVIDIA
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
VirusTotal
63/63 vendors flagged this skill as clean.
Static analysis
Detected: suspicious.prompt_injection_instructions