monday-brief
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Local File System Interaction: The skill uses the Bash tool to write generated briefing files directly to the user's local directory (
~/Desktop). While this is part of the skill's stated purpose, local file system modifications represent a security consideration for system integrity. - Processing of External Untrusted Data: The skill ingests and summarizes content from external sources including Gmail and Slack, which creates a potential surface for indirect prompt injection if those messages contain embedded instructions.
- Ingestion points: Data is retrieved from QuickBooks, PayPal, HubSpot, Google Calendar, Gmail, and Slack messages as described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or instructions to differentiate between data and control commands when processing external text.
- Capability inventory: The skill utilizes local shell access via the
Bashtool for file creation and possesses the capability to post content to Slack and Microsoft Teams. - Sanitization: There is no evidence of content filtering or sanitization performed on the messages retrieved from external platforms before they are processed by the agent.
Audit Metadata