clawddocs
Security checks across malware telemetry and agentic risk
Overview
This documentation skill is not malicious, but it asks for a sensitive API key and tells agents to run helper scripts that are not actually included in the package.
Install only if you are comfortable providing SKILLBOSS_API_KEY to this skill and can verify what that key can access. Before allowing any ./scripts/*.sh command to run, confirm the publisher supplies the missing scripts/snippets or inspect the local execution path so unrelated project scripts are not run by mistake.
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
66/66 vendors flagged this skill as clean.