daily-ui-inspiration-capture

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Node.js script located at scripts/check-ui-inspiration-duplicates.mjs to validate the generated manifest metadata.
  • [COMMAND_EXECUTION]: Utilizes Git shell commands including git status and git add -f to manage workspace changes and stage specific article directories.
  • [PROMPT_INJECTION]: The skill extracts content from external landing pages and design sites to generate AI-builder prompts and summaries, which presents an indirect prompt injection surface.
  • Ingestion points: External website content captured via the in-app browser.
  • Boundary markers: No explicit delimiters are instructed for use when interpolating captured external text into generated Markdown content.
  • Capability inventory: File system write access to articles/, shell command execution via Node.js and Git, and browser-based network access.
  • Sanitization: No evidence of sanitization or validation of the extracted external data before it is used in prompt generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 06:56 PM
Security Audit — agent-trust-hub — daily-ui-inspiration-capture