NYC
skills/smithery/ai/tinybird/Gen Agent Trust Hub

tinybird

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (CRITICAL): The file 'rules/sql.md' was flagged by the URLite scanner for containing a blacklisted malicious URL (Reference ID: URE40E38848FEE8F9C-0200). This indicates a high risk of the agent interacting with known malicious domains or downloading harmful content.
  • PROMPT_INJECTION (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8). Ingestion points: The skill processes untrusted Tinybird project files such as .datasource, .pipe, and .connection. Boundary markers: Absent; there are no instructions or delimiters to help the agent distinguish between its system rules and potentially malicious instructions embedded in the project files. Capability inventory: The skill facilitates the creation and modification of data files and SQL queries. Sanitization: Absent; no input validation or sanitization mechanisms are described for the external data files processed.
Recommendations
  • AI detected serious security threats
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 17, 2026, 06:49 PM