frontend-task-breakdown
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Technical analysis reveals that the skill follows established safety protocols and contains no malicious code, obfuscation, or hidden logic.
- [PROMPT_INJECTION]: The skill ingests untrusted data from design handoffs and PRD files, representing a surface for indirect prompt injection. Mandatory Evidence Chain: 1. Ingestion points: $ARGUMENTS and PRD files; 2. Boundary markers: Absent; 3. Capability inventory: Write, Bash (cp), and Edit tools; 4. Sanitization: Not specified. The risk is mitigated by requiring explicit user approval before performing any write operations in Phase 2.
- [COMMAND_EXECUTION]: The skill uses restricted bash commands and configuration editing tools that are limited to the plugin's environment and necessary for its primary function.
Audit Metadata