ScienceClaw: Agent Status
Security checks across malware telemetry and agentic risk
Overview
This is a local status helper for ScienceClaw that reads existing agent memory and reports activity, with no packaged executable code or hidden transfer behavior found.
Install this only if you use and trust the local ScienceClaw installation it will invoke. Review output before sharing it, because journal entries, topics, and graph searches may reveal private research activity. Do not expose ANTHROPIC_API_KEY for this status skill unless another trusted ScienceClaw component separately requires it.
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.