sales-monday-notetaker

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill operates as a purely informational resource for integrating and managing the monday.com AI Notetaker platform. No malicious code, obfuscation, or unauthorized access patterns were detected.
  • [EXTERNAL_DOWNLOADS]: References official documentation and tools from monday.com (e.g., api.monday.com, developer.monday.com), which are established and well-known technology services.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill documents the use of meeting transcripts and summaries retrieved via the notetaker.meetings GraphQL API endpoint (file: references/monday-notetaker-api-reference.md).
  • Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions for the transcript data itself.
  • Capability inventory: The skill does not possess capabilities for command execution, local file system modification (beyond its own learning file), or network exfiltration of ingested data.
  • Sanitization: No sanitization methods for meeting data are discussed or implemented.
  • Result: While the skill involves processing untrusted external data (meeting transcripts), the absence of dangerous capabilities minimizes the potential for exploitation via indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 08:26 AM
Security Audit — agent-trust-hub — sales-monday-notetaker