skills/miroapp/miro-ai/miro-browse/Gen Agent Trust Hub

miro-browse

Pass

Audited by Gen Agent Trust Hub on May 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary purpose is to help users browse and filter items on Miro boards, which is a common and legitimate use case for productivity agents.
  • [SAFE]: All identified tools (board_list_items, context_explore, context_get, image_get_url, image_get_data, doc_get) are Miro-specific utilities provided by the vendor to interact with their platform.
  • [SAFE]: The skill correctly identifies and extracts Miro board IDs and item IDs from standard Miro URLs, including those with focus parameters like moveToWidget.
  • [SAFE]: No signs of prompt injection, data exfiltration, or unauthorized command execution were found. The skill operates within the expected boundaries of the Miro platform.
  • [SAFE]: Indirect Prompt Injection Risk: Although the skill processes external data (Miro board content like sticky notes and text), it lacks dangerous capabilities like system-level code execution or file writes that would make this ingestion highly risky. The risk is consistent with standard data retrieval tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
May 21, 2026, 11:26 AM
Security Audit — agent-trust-hub — miro-browse