Security audit
Refines ambiguous or high-risk user requests before execution. Trigger when the request is underspecified, likely to benefit from clearer constraints or verification, or when the user explicitly asks to refine, improve, optimize, refactor, or compare approaches. Skip clear single-step instructions and already-well-scoped tasks.
Security checks across malware telemetry and agentic risk
Overview
This is a transparent prompt-refinement skill with no bundled code, credential use, network use, or hidden install behavior.
Reasonable to install if you want an agent to refine vague prompts before acting. Expect occasional clarification or compare-first prompts, and be aware that if used with a separate session-learning skill it may pass only abstract preference labels, not full prompt text.
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.