agent-orchestration-planner

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill demonstrates patterns for building agent prompts that are susceptible to Indirect Prompt Injection (Category 8).
  • Ingestion points: Untrusted data enters the prompt via the query variable in select_tools and the state.get_context() method in build_planning_prompt (SKILL.md).
  • Boundary markers: Absent. The code uses simple f-string interpolation (e.g., Given this query: "{query}") without delimiters like XML tags or triple quotes to separate instructions from data.
  • Capability inventory: The orchestration logic handles high-privilege tools including query_database, call_api, and search_web (SKILL.md).
  • Sanitization: Absent. There is no escaping or validation of the user-provided strings before they are sent to the LLM.
  • DATA_EXFILTRATION (SAFE): No evidence of hardcoded credentials or unauthorized network operations. The defined network/database tools are conceptual and part of the stated orchestration purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:41 PM