Skills
skills/tencentcloudbase/skills/relational-database-mcp-cloudbase/Gen Agent Trust Hub

relational-database-mcp-cloudbase

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references external documentation and sibling skills hosted on the vendor's repository at cnb.cool. These resources (e.g., https://cnb.cool/tencent/cloud/cloudbase/cloudbase-skills/-/git/raw/main/skills/cloudbase/SKILL.md) are vendor-owned and used for legitimate architectural guidance.
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection as it processes untrusted data from a relational database.
  • Ingestion points: Data enters the agent's context through the querySqlDatabase tool output.
  • Boundary markers: Absent. The skill suggests using SQL LIMIT for data management but does not define markers to separate untrusted data from instructions.
  • Capability inventory: The skill possesses high-privilege capabilities including database modification (manageSqlDatabase) and permission management (managePermissions).
  • Sanitization: No sanitization or validation of database content is specified before the data is integrated into the prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 11:45 AM