api-baas-turso

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The reference.md file includes a command to fetch and execute the official Turso CLI installation script from get.tur.so. This is a standard installation method for the associated service.
  • [PROMPT_INJECTION]: Potential surface for indirect prompt injection through database query results.
  • Ingestion points: Database rows fetched using client.execute() and client.batch() across various example files.
  • Boundary markers: Absent; query results are directly mapped to variables without specific delimiters to distinguish data from instructions.
  • Capability inventory: The skill is intended for use by agents with database access capabilities, which may also possess file system and network execution permissions.
  • Sanitization: No sanitization or validation of the retrieved database content is demonstrated in the code patterns before the data is processed or returned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 01:31 AM