frontend-design
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to execute a local Python script for task validation:python3 workflows/validate_tasks.py .maestro/<slug>/frontend/tasks.json. This is a standard validation pattern for this type of automated workflow. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the local codebase.
- Ingestion points: The skill uses
Read,Grep, andGlobtools to scan existing application code, routing, and component libraries. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the source code comments or strings.
- Capability inventory: The skill possesses file-writing capabilities (
Write) and shell command execution (Bash). - Sanitization: No sanitization or filtering logic is applied to the content read from the codebase before it is used to generate the LLD and task list.
Audit Metadata