Postgrest
Security checks across malware telemetry and agentic risk
Overview
This PostgREST skill is coherent, but it can give an agent broad authenticated access to read, create, update, or delete live database records without explicit approval safeguards.
Install only if you are comfortable giving Membrane-mediated access to the target PostgREST API. Use a least-privileged or read-only database role where possible, verify the connection and endpoint before each operation, and require explicit user approval before any request that creates, updates, or deletes records.
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
65/65 vendors flagged this skill as clean.