Slack Block Kit

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Potential for indirect prompt injection as the skill processes external sales data (e.g., transcripts, CRM notes) to generate Slack notifications.
  • Ingestion points: The data input parameter in SKILL.md receives message-specific content from external sales workflows.
  • Boundary markers: Documentation in references/block-types-and-limits.md specifies the use of safeMrkdwn() and safeHeaderText() helpers to wrap content.
  • Capability inventory: The skill utilizes the slack capability and executes POST requests to a send-slack-message edge function.
  • Sanitization: Implements safety wrappers (safeButtonText, safeFieldText) for text truncation and Slack-specific formatting safety.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:38 AM