Security audit
LangSkills Search
Security checks across malware telemetry and agentic risk
Overview
This is a straightforward offline search helper, with the main caution that it asks users to install a third-party Python package and data bundles.
Install only if you trust the `langskills-rai` package source, preferably in an isolated Python environment. Treat returned full skill bodies as reference material and verify commands before copying them into an agent workflow.
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.
Static analysis
No suspicious patterns detected.