ideate
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill architecture creates a surface for indirect prompt injection by processing data from external sources.
- Ingestion points: The skill fetches content from external Figma links and other reference materials provided by the user as noted in the reference_capture and process sections of SKILL.md.
- Boundary markers: There are no instructions to use boundary markers or safety delimiters when incorporating this external content into the agent context.
- Capability inventory: The agent possesses the capability to write files to the repository and execute git commands, providing a mechanism for an injection to persist changes or perform actions.
- Sanitization: The process lacks explicit sanitization or filtering of data retrieved from external sources before it is processed.
- [DYNAMIC_EXECUTION]: The skill dynamically loads specialized sub-agents from local paths.
- Evidence: The workflow involves spawning agents such as agents/workflow/spec-document-reviewer.md and agents/workflow/spec-flow-analyzer.md to perform checks on the generated content.
- [COMMAND_EXECUTION]: The skill utilizes system commands for repository management.
- Evidence: It explicitly uses git add and git commit to store feature specifications in the local development environment.
Audit Metadata