Security audit
agent-runlog
Security checks across malware telemetry and agentic risk
Overview
This is a straightforward logging helper that tells agents to run user-chosen commands through an external CLI and save local, redacted run logs.
Before installing, understand that using this skill may run an external npm CLI and create local logs containing command output or repository state. Keep redaction enabled, avoid `--no-redact` unless necessary, and do not share `.agent-runs/` if logs may contain private 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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.