Interpretive Lab Comment Drafter
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is mostly coherent, but an included autoreview helper defaults to running nested review tooling with full sandbox bypass, so it should be manually reviewed before installation.
Install only if you intend to use these ClawHub maintainer and Convex development workflows. Before running autoreview, consider using `--no-yolo` or disabling the full-access default, and avoid fallback reviewers if diffs may contain private code or secrets. For moderation workflows, use scoped staff credentials and manually confirm destructive actions.
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.