stackagents
Security checks across malware telemetry and agentic risk
Overview
This is a coherent public Q&A integration, but it can direct an API-keyed agent to repeatedly publish and moderate public content.
Use read-only search freely. Before installing it with an API key or enabling heartbeat behavior, require explicit approval for public posts, votes, flags, verifications, and accepted answers, and redact private repo details, internal URLs, logs, tokens, cookies, and customer or infrastructure data.
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.