pushary-cowork

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for utilizing Pushary tools to enhance agent-user communication during long-running or sensitive tasks.
  • [DATA_EXFILTRATION]: The skill instructions involve sending task-related information and questions to the external domain pushary.com. This behavior is the primary intended function of the Pushary connector and is consistent with the vendor's service model.
  • [PROMPT_INJECTION]: The agent is instructed to ingest and act upon responses received from the user's phone. This represents a standard input surface where the user provides feedback to guide the agent's next steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 04:19 PM
Security Audit — agent-trust-hub — pushary-cowork