Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:201
Security audit
tuanzi-guardianclaw
Security checks across malware telemetry and agentic risk
Overview
This defensive prompt-only skill is not malware, but it asks to act as an always-on security kernel that overrides other skills without clear platform enforcement or user-controlled scope.
Install only if you want an advisory security-policy prompt. Do not rely on it as a real sandbox or enforcement layer, and review carefully before allowing it to override other skills, block requested work, or create audit logs containing file paths or attempted actions.
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