Security audit
RTFM Testing
Security checks across malware telemetry and agentic risk
Overview
This skill appears to be a scoped documentation-testing helper that spawns a constrained tester agent and does not show evidence of exfiltration, destructive behavior, persistence, or hidden authority.
Before installing, understand that the skill may spawn a separate tester agent to evaluate documentation. That is appropriate for its purpose, but use it when you are comfortable sharing the relevant documentation with that spawned session and reviewing its output for literal gap reports rather than inferred answers.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.