Ingestigate Investigative intelligence for AI agents
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed Ingestigate integration for searching and processing investigative document corpuses through the user's configured account.
Install only if you trust Ingestigate with the document corpuses involved. Configure the token and base URL only through secure skill settings, confirm that uploads and retention fit your organization's policies, and review any advanced workflow or script guidance fetched from the provider before allowing high-impact processing.
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.