Security audit
CoinMarketCap
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly purpose-aligned, but the autoreview helper defaults to running a nested Codex review with full-access sandbox bypass, which is too much authority for a review workflow.
Install only if you are comfortable with repo-maintainer workflows that use GitHub, Convex, and moderation credentials. For safer use, run the autoreview helper with `--no-yolo` or `AUTOREVIEW_YOLO=0`, disable fallback reviewers unless you intend to share diffs with them, and require explicit confirmation for any moderation or publishing action.
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
56/56 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.