Security audit
Docmosis
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly coherent, but the autoreview helper defaults to running nested Codex with sandbox and approval bypass, which is broader access than a review workflow needs.
Review the autoreview helper before installing or invoking it. Prefer running it with `--no-yolo` or `AUTOREVIEW_YOLO=0`, and only use moderation, migration, proof publishing, or GitHub comment workflows when you intend the agent to make those external changes.
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.