Security audit
Hindsight Bias
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are purpose-aligned and disclose their higher-impact actions with user confirmation and scoped workflows.
Install only in workspaces where you expect these skills to guide administrative ClawHub, Convex, documentation, or AI review tasks. Reviewers and admin workflows may send code or command output to configured tools and can perform account, moderation, or email actions when explicitly confirmed, so use them with the intended authenticated accounts and check commands before approving writes.
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.