Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- README.md:40
Security audit
CISO Agent Security
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed, instruction-only security assessment skill, with operational cautions around any real quarantine or patch authority granted to the receiving agent.
Safe to install as a security reference skill. If the receiving agent has real tools that can quarantine agents, modify prompts, or generate patches, keep those actions scoped, logged, reversible, and subject to human approval.
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
65/65 vendors flagged this skill as clean.
Static analysis
Detected: suspicious.prompt_injection_instructions