frontend-design-extractor

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell scripts located within the skill's directory structure, specifically scripts/scan_ui_sources.sh and scripts/generate_output_skeleton.sh. These scripts are used to scan local repositories and create output directories, which involves direct filesystem interaction.
  • [PROMPT_INJECTION]: The skill is designed to process untrusted data from existing codebases, creating a surface for indirect prompt injection. Malicious instructions embedded in source code, comments, or documentation of the analyzed project could potentially influence the agent's behavior during the extraction process.
  • Ingestion points: Files within the target codebase scanned by scripts/scan_ui_sources.sh.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined in the skill.
  • Capability inventory: The agent has the capability to read local files, write to a designated ui-ux-spec/ folder, and execute the referenced shell scripts.
  • Sanitization: The instructions do not specify any validation or sanitization of the content extracted from the codebase before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 07:08 AM