Content Gen
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent content-drafting helper that reads user-selected project materials and writes a local draft content pack, with no hidden execution or credential use found.
Install only if you want an agent to read project documentation and create a draft docs/content-pack.md file. Provide project paths deliberately, avoid pointing it at sensitive files, review the generated copy before publishing, and be aware that optional solograph MCP tools may access project or code context if configured.
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.