Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:3
Security audit
Alex
Security checks across malware telemetry and agentic risk
Overview
This is a simple research-assistant skill that asks the agent to search the web and cite sources, with no hidden installer, persistence, credential access, or destructive behavior found.
This skill is reasonable to install for general web research. Because it always searches the web, avoid giving it confidential topics or private business details unless you are comfortable with those search queries being sent to external search providers.
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
64/64 vendors flagged this skill as clean.
Static analysis
Detected: suspicious.prompt_injection_instructions