dispatch-reviewers-workflow
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute external command-line interfaces, specifically 'Claude Code CLI' and 'Codex CLI', to perform sub-agent dispatches.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the content it processes.
- Ingestion points: The 'review target' (code or documentation provided by the user) is passed to sub-agents for evaluation (SKILL.md).
- Boundary markers: Absent. The instructions do not specify any delimiters or warnings to isolate the untrusted review target from the agent's instructions.
- Capability inventory: The agent dispatches sub-agents using external CLI tools which can execute code or access files depending on the sub-agent's configuration (SKILL.md).
- Sanitization: Absent. There is no mention of filtering, escaping, or validating the 'review target' content before it is processed by the sub-agents.
Audit Metadata