fable-codex-setup

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @openai/codex CLI tool and associated plugins. These are resources associated with the official OpenAI organization.
  • [COMMAND_EXECUTION]: The codex-executor sub-agent is designed to execute the codex exec command via the Bash tool to perform bulk code implementation tasks as part of its core functionality.
  • [INDIRECT_PROMPT_INJECTION]: The orchestration architecture creates an attack surface where untrusted user input is processed by the primary agent and delegated to sub-agents.
  • Ingestion points: User-defined goals and context files are processed by the Fable 5 orchestrator (SKILL.md, templates/CLAUDE-orchestration.md).
  • Boundary markers: Not explicitly defined in the provided sub-agent templates for input separation.
  • Capability inventory: The codex-executor sub-agent has access to the Bash tool to modify the filesystem and execute CLI commands (templates/agents/codex-executor.md).
  • Sanitization: The skill mitigates risks by instructing the agent to always verify sub-agent output using git diff --stat and automated success-criterion commands before integration.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 04:42 AM