do-page
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from various documentation and design files which are then used to guide sub-agents in generating code and executing commands.
- Ingestion points: The skill reads files from
docs/specs/page-UCS/,docs/product/demo/,docs/specs/design/COMPONENTS.md, and API definitions. - Boundary markers: Absent; instructions do not include delimiters or warnings to ignore embedded instructions in the processed data.
- Capability inventory: The agent can write arbitrary source code to the project and execute shell commands including Python scripts and build tools (
npm,flutter,tsc). - Sanitization: Absent; content from external files is interpolated into prompts without validation or escaping.
- [COMMAND_EXECUTION]: The skill executes a local utility script
scripts/slice-page.pyand triggers project-specific build commands defined in the project's tech stack rules. - [DYNAMIC_EXECUTION]: The orchestration logic dynamically constructs and executes build commands based on the technical stack identified in the project's documentation (
tech-stack-rule.md).
Audit Metadata