ui-social-feed-shell

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines a standard user interface shell for a Next.js application. It uses local development tools like bun and ripgrep for validation, which is consistent with its stated purpose and development best practices.\n- [PROMPT_INJECTION]: The skill facilitates the ingestion of external social feed data through a source adapter, which constitutes an indirect prompt injection surface (Category 8).\n
  • Ingestion points: Untrusted data enters the agent context through the FEED_SOURCE_ADAPTER and is rendered in the timeline components.\n
  • Boundary markers: The skill does not implement delimiters or instructions to ignore potential commands embedded in the feed data.\n
  • Capability inventory: The skill's operational footprint is limited to generating UI code and performing local shell-based file existence and content checks; it lacks network access or dynamic execution capabilities.\n
  • Sanitization: No explicit content sanitization or escaping logic is provided in the template code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 10:59 AM