skills/jream/ai-skills/turso/Gen Agent Trust Hub

turso

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches CLI installation scripts from Turso's official domains (get.tur.so and get.turso.tech).
  • [REMOTE_CODE_EXECUTION]: Provides instructions for installing the Turso CLI and AgentFS via shell-piped remote scripts (curl | bash), which is the standard installation method for these tools.
  • [PROMPT_INJECTION]: The documentation for AgentFS describes a filesystem for AI agents, which introduces a surface for indirect prompt injection. \n
  • Ingestion points: Filesystem read operations (e.g., fs.read_file(), agentfs run) where the agent processes content from a virtual filesystem. \n
  • Boundary markers: No specific delimiters or instruction-ignore warnings are specified in the documentation. \n
  • Capability inventory: The skill documents capabilities including shell command execution (agentfs run bash), database queries, and filesystem writes. \n
  • Sanitization: No explicit sanitization or validation of file content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 12:13 PM
Security Audit — agent-trust-hub — turso