sp-new-ui-mock
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill relies on the agent writing a Python generator script (
gen.py) and then executing it viapython3. This dynamic generation and execution of code is a core part of the workflow but presents a runtime execution risk. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow the contents of
PRD.mdto ground the design content. Because this file is an external data source, it could be used to inject instructions that influence the agent's code generation. - Ingestion points:
PRD.md(referenced in Step 2). - Boundary markers: None specified to differentiate data from instructions.
- Capability inventory: Execution of shell commands (
sp,refkit,python3), file system modification (mkdir,cp,.gitignoreupdates). - Sanitization: No sanitization of the PRD content is described before use in script generation.
- [COMMAND_EXECUTION]: The skill executes various command-line utilities including
sp,refkit, andmkdir. It also suggests executing a shell installation script (install.sh) to set up the required environment.
Audit Metadata