build
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's workflow exposes the agent to potential indirect prompt injection attacks.
- Ingestion points: Untrusted data enters the agent context via web search results during the 'Deep Research' and 'Conduct Phase Research' steps, as well as through reading existing codebase files to understand patterns (SKILL.md).
- Boundary markers: The instructions do not specify any delimiters or safety warnings to prevent the agent from accidentally executing instructions found within the research materials or codebase.
- Capability inventory: The skill utilizes web search, local filesystem read/write, and interactive user questioning tools (SKILL.md).
- Sanitization: There is no logic provided to sanitize or filter the content retrieved from external sources before it is processed or used to generate implementation plans.
Audit Metadata