stage-gates
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions and configuration files. It does not contain any executable scripts (Python, JavaScript, shell) or commands.
- [SAFE]: The skill operates as a high-level manager for workflow state. It identifies stages, defines gates, and routes the agent to other specialized skills within the local environment based on the workflow stage.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests untrusted data in the form of user-defined recipe stages and acceptance criteria, it uses structured Markdown tables as boundary markers and has no direct capability to execute code or exfiltrate data, mitigating the risk. * Ingestion points: Recipe stages and criteria provided via user input or upstream skills (SKILL.md). * Boundary markers: The skill explicitly uses Markdown tables and checklists to define and evaluate gates (SKILL.md, references/gate-template.md). * Capability inventory: No execution capabilities, file system writes, or network operations are present in this skill. * Sanitization: None explicitly mentioned, but the skill relies on the agent's interpretative structure and the lack of underlying dangerous tools.
Audit Metadata