skills/pingcap/agenticstore/tidbx/Gen Agent Trust Hub

tidbx

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides instructions to install the TiDB Cloud CLI by downloading a script from the official GitHub repository and piping it to the shell. This is the documented installation method for the vendor tool.
  • [COMMAND_EXECUTION]: Authentication workflows suggest using the --insecure-storage flag with the ticloud auth login command, which allows the CLI to manage session tokens locally.
  • [CREDENTIALS_UNSAFE]: Reference command patterns for SQL user management include the --password flag, which involves passing secrets as plain-text command-line arguments. This is a common pattern in CLI documentation.
  • [PROMPT_INJECTION]: The skill ingests JSON data from the CLI to render ASCII tables, creating a potential surface for indirect instructions if resource metadata is maliciously crafted.
  • Ingestion points: Output from ticloud serverless list and ticloud project list (SKILL.md).
  • Boundary markers: No explicit delimiters are used to separate ingested data from the prompt context.
  • Capability inventory: Creation and deletion of cloud clusters and branches via CLI commands (references/ticloud.md).
  • Sanitization: Data is parsed and formatted into tables without explicit validation or escaping of the string content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 04:20 PM