reasoning-orchestrator

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a purely instructional framework designed to help the agent triage problems and select appropriate reasoning methodologies. It does not perform any sensitive operations.\n- [PROMPT_INJECTION]: The skill contains logic for interpolating untrusted user data into prompts for subagents, creating a surface for indirect prompt injection.\n
  • Ingestion points: User-provided problem descriptions are ingested in the SKILL.md file and passed to subagents.\n
  • Boundary markers: The subagent prompt template uses delimiters like 'Context:' and 'Your task:' to help separate user input from instructions.\n
  • Capability inventory: This skill does not use any subprocess calls, file-system writing, or network operations.\n
  • Sanitization: No input sanitization or validation is applied to the user-provided problem description before it is used in subagent tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:21 AM