Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:14
Security audit
Content Security Filter
Security checks across malware telemetry and agentic risk
Overview
This is a defensive content-scanning skill with disclosed file, text, stdin, and URL scanning behavior that matches its stated purpose.
Reasonable to install as a defensive pre-check. Only scan files and URLs you intentionally choose, avoid sharing JSON output if it contains private text, and do not treat a SAFE result as proof that content is fully harmless.
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