Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- references/advanced-patterns.md:144
Security audit
Agent Docs
Security checks across malware telemetry and agentic risk
Overview
This skill is a documentation guide, and its security-related examples are presented as warnings and mitigations rather than actions to perform.
Safe to install as a documentation aid. Review any generated AGENTS.md, SKILL.md, llms.txt, README, or CI snippets before committing them, and keep security examples clearly labeled so future agents do not treat them as live instructions.
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