Security audit
Abyssale
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are coherent developer and ClawHub staff-operation helpers with disclosed high-impact actions guarded by explicit targets, confirmations, dry runs, and existing authenticated CLIs.
Install only if you intend to use ClawHub/Convex operator workflows or the autoreview helper. For moderation, correspondence, and production migrations, confirm exact targets and dry-run results before any write. For autoreview, remember that selected model CLIs may receive code diffs, so avoid running it on secrets or sensitive private changes unless that provider use is acceptable.
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
61/61 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.