Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:30
Security audit
Agent Security Hardening
Security checks across malware telemetry and agentic risk
Overview
This is a defensive, instruction-only security-hardening guide with risky-looking text framed as examples of attacks to block.
Reasonable to install as a defensive reference. Before copying any shell snippets into production, review the health-check script, decide whether the Anthropic API call is necessary, protect API keys, and make any cron or monitoring setup an explicit operator action.
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