Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:33
Security audit
OWASP Top 10 AI
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only security guardrail skill that makes the agent more cautious about OWASP LLM risks, with no executable code or hidden access found.
Install this if you want OWASP-style LLM security guardrails. Expect more conservative behavior, including refusals or confirmation prompts around sensitive data, external tools, generated code execution, system prompt requests, and large or open-ended tasks. Review any separately downloaded organization-specific replacement skill before using it.
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