Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:3
Security audit
Guardian Wall
Security checks across malware telemetry and agentic risk
Overview
Guardian Wall is a coherent defensive skill that locally sanitizes untrusted text and flags prompt-injection patterns without hidden persistence, network access, or destructive behavior.
Reasonable to install as a lightweight prompt-injection aid. Treat its detections as heuristics rather than complete protection, and avoid sending sensitive content to an audit sub-agent unless the agent environment is appropriately constrained.
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
66/66 vendors flagged this skill as clean.
Static analysis
Detected: suspicious.prompt_injection_instructions