admin-meeting-prep

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides installation instructions using npx to fetch the zynkr-skill-builder tool from the author's GitHub repository (github.com/peter-tu-zynkr).
  • [COMMAND_EXECUTION]: The skill invokes tools to access sensitive user data, including reading Google Calendar events and searching Gmail messages, and sends information to Google Chat via mcp__google_workspace tool invocations.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources such as email messages and raw meeting transcripts to generate summaries.
  • Ingestion points: Gmail message search results in SKILL.md and raw input notes in agents/admin-meeting-note.md.
  • Boundary markers: None implemented to distinguish external data from system instructions.
  • Capability inventory: The skill uses the mcp__google_workspace__google_chat_send_self_message tool to output processed content.
  • Sanitization: No specific sanitization or filtering logic is described for the email background or meeting note inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:31 PM
Security Audit — agent-trust-hub — admin-meeting-prep