daily-ui-inspiration-capture

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local shell commands including git status, git add, and node scripts/check-ui-inspiration-duplicates.mjs for repository management and data integrity checks. These operations are internal to the workspace and support the core functionality of maintaining a design bundle repository.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes data from external web sources. Evidence chain: 1. Ingestion points: Web content retrieved from landing pages and galleries (e.g., Framer, Dribbble) via the browser. 2. Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the captured data. 3. Capability inventory: The skill has file-write permissions for creating the dated bundle folders and executes local shell commands for validation. 4. Sanitization: There is no explicit mention of sanitizing or escaping the content scraped from the web before it is written to the project's Markdown and JSON files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 03:08 AM
Security Audit — agent-trust-hub — daily-ui-inspiration-capture