Security audit
Cue Capital Operations
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed Cue research workflow that installs or updates a public runner and requires confirmation before spending credits.
Install only if you are comfortable using Cue for capital-markets research, cloning the external cue-skills runner, and letting it read your Cue API key from ~/.cue/config.json. Confirm the credit spend prompt before each deep research run and treat outputs as public-data research, not legal, underwriting, or due-diligence advice.
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
63/63 vendors flagged this skill as clean.