Security audit
Writing Plans
Security checks across malware telemetry and agentic risk
Overview
This is a low-risk planning helper that only tells an agent how to write structured implementation plans.
Before installing, understand that the skill may lead your agent to create a plan file in docs/plans/ and suggest verification commands. Review those generated commands before running them, but there is no evidence of hidden execution, credential access, exfiltration, or unrelated behavior.
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.