dingtalk-tb-ai-skill

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The README.md file contains standard installation instructions for the 'uv' package manager via 'astral.sh'. This is a well-known and widely used tool in the Python development ecosystem and is treated as a safe external reference.\n- [PROMPT_INJECTION]: The skill manages tasks and projects by constructing TQL (Teambition Query Language) strings from user-provided input, which represents an indirect prompt injection surface.\n
  • Ingestion points: Command-line arguments used as search filters in scripts like 'scripts/query-tasks.py' and 'scripts/query-projects.py'.\n
  • Boundary markers: None are explicitly implemented in the script logic to separate user data from query instructions.\n
  • Capability inventory: The skill performs authenticated network requests to 'open.teambition.com' and executes internal scripts via subprocesses.\n
  • Sanitization: User input is interpolated into query strings without dedicated sanitization, relying on the Teambition API's permission model to restrict data access.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 09:08 PM