model-roundtable

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes several internal Python scripts (e.g., run_codex.py, run_gemini.py, run_kimi.py, runner_jobs.py) and CLI utilities (such as agy and kimi-cli) via shell commands to launch and manage model roundtable seats. These executions are part of the core functionality described in references/runner-invocations.md.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it interpolates untrusted user content into the instructions for multiple sub-agents.
  • Ingestion points: Raw user prompts and context file paths enter the context in SKILL.md for both opening and discussion rounds.
  • Boundary markers: The skill uses XML-style delimiters (e.g., <original prompt>) to separate untrusted data from the agent instructions.
  • Capability inventory: It executes shell-based runners and spawns Agent sub-agents as detailed in references/runner-invocations.md.
  • Sanitization: No explicit escaping or sanitization of the user-provided input is specified, relying on the seats' instructions to remain in a "read-only" interpretation mode.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 09:49 PM
Security Audit — agent-trust-hub — model-roundtable