Daily Wisdom
Security checks across malware telemetry and agentic risk
Overview
The skill appears to be a low-impact writing aid with disclosed memory and verification behavior, and the reported prompt-injection concern is a generic design risk rather than evidence of abuse.
Install only if you are comfortable with the agent using a local anecdote-history file and web results as context. Treat the history file as untrusted editable text: do not place secrets in it, and review or clear it if other tools or people can modify it.
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.