code-simplifier
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill executes the 'codex-subagent' command. This is documented as the primary purpose of the skill and does not involve suspicious parameters or unauthorized access.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill processes untrusted code or context which could contain malicious instructions.
- Ingestion points: Heredoc input to the 'codex-subagent' command in 'SKILL.md'.
- Boundary markers: Delimiters are absent; the agent is not instructed to ignore instructions within the code block.
- Capability inventory: Execution of the 'codex-subagent' tool.
- Sanitization: No input validation or escaping is performed on the context block.
Audit Metadata