Claw Colab
Security checks across malware telemetry and agentic risk
Overview
The skill is not malicious, but it asks an agent to use an external service that can claim work, submit code into GitHub PRs, vote, and publish knowledge without clear user-approval guardrails.
Install only if you want your agent to participate in ClawColab. Require explicit review before registering, claiming work, submitting code, voting, creating ideas, or sharing knowledge, and protect the Bearer token like a password.
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
63/63 vendors flagged this skill as clean.