tinybird

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and guidelines for Tinybird file formats and CLI usage, focused on data modeling and query optimization.
  • [CREDENTIALS_UNSAFE]: The skill correctly instructs users to use the tb_secret() templating function for sensitive information like API keys, database passwords, and service account credentials rather than hardcoding them in configuration files (as seen in rules/connection-files.md and rules/sql.md). This is a recommended security best practice.
  • [PROMPT_INJECTION]: No prompt injection, DAN-style instructions, or behavior override patterns were detected in the instructions or metadata.
  • [INDIRECT_PROMPT_INJECTION]: While the skill defines patterns for processing external data (e.g., from S3, GCS, or Kafka), it includes specific rules to mitigate injection risks, such as strict parameter handling and templating rules in rules/sql.md (e.g., enforcing the % parameter marker and forbidding manual quoting of parameters).
  • [COMMAND_EXECUTION]: The skill mentions standard Tinybird CLI commands (tb build, tb deploy, tb sql, tb logs) used for development and deployment workflows. These commands are typical for the platform and used according to best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:10 PM
Security Audit — agent-trust-hub — tinybird