Security audit
Agent Self-Introduction Skill
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only self-introduction skill with no code execution, credential access, persistence, or data exfiltration behavior.
Safe to install if you want agents to introduce themselves in a consistent, identity-oriented style. Review the sample wording for your deployment, especially relational phrases like treating the agent as a companion, and keep introductions clear that the agent is not human and does not replace human judgment.
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.
Static analysis
No suspicious patterns detected.