Security audit
OpenSpace Skill Discovery
Security checks for vulnerabilities and agentic risk
Overview
This skill is a small discovery helper, but it can automatically import community skills and then have the agent follow their instructions without a clear approval gate.
Install only if you are comfortable with a discovery tool that may import community skills during search. Prefer setting auto_import to false, review any imported SKILL.md before letting the agent follow it, and be cautious if cloud search requires an account or API key.
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
Static analysis
No suspicious patterns detected.