type-design-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
codex-subagentcommand-line tool to perform its primary function of type design evaluation. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input, such as task context, scope, and issue/PR numbers, which are passed directly to the subagent via a shell heredoc.
- Ingestion points: User-provided task context and issue metadata in
SKILL.md. - Boundary markers: Utilizes shell heredoc delimiters (
EOF) to separate the input content. - Capability inventory: The skill triggers shell command execution through the
codex-subagentutility. - Sanitization: There is no evidence of explicit sanitization or filtering of the external data before it is passed to the subagent process.
Audit Metadata