skills/davekilleen/dex/meeting-prep/Gen Agent Trust Hub

meeting-prep

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by aggregating data from untrusted external sources into a single brief. \n
  • Ingestion points: Local files in 05-Areas/People/, 04-Projects/, and 00-Inbox/Meetings/, as well as remote content from Slack messages, Microsoft Teams chats, Gmail threads, and Notion pages. \n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the output format instructions. \n
  • Capability inventory: The skill can read local files, call external MCP tools for searching third-party integrations, and write to System/usage_log.md. \n
  • Sanitization: No evidence of sanitization, filtering, or validation of content retrieved from external integrations before it is presented to the user. \n- [DATA_EXFILTRATION]: The skill performs telemetry by calling a track_event function with metadata (attendees_count). It also accesses sensitive configuration files, including System/user-profile.yaml (containing user profile data) and System/integrations/config.yaml (containing integration statuses). \n- [COMMAND_EXECUTION]: The skill utilizes Model Context Protocol (MCP) tools to interact with external services (Notion, Slack, Teams, Google Workspace) and perform semantic searches via QMD. While these are platform-provided tools, they represent the execution of logic against external data sets.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 01:27 AM