add-slack

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches and merges Slack integration source code from the author's GitHub repository (github.com/qwibitai/nanoclaw-slack.git).
  • [COMMAND_EXECUTION]: Uses git to manage the integration of new source code and launchctl to restart the com.nanoclaw service on macOS to apply configuration changes.
  • [CREDENTIALS_UNSAFE]: Instructs the user to store Slack Bot and App tokens (xoxb-... and xapp-...) in a local .env file for authentication. This follows standard secret management practices for the platform.
  • [PROMPT_INJECTION]: As the skill enables the agent to process messages from external Slack channels, it introduces a surface for indirect prompt injection.
  • Ingestion points: Incoming messages via the Slack Socket Mode connection.
  • Boundary markers: Not explicitly defined in the setup instructions.
  • Capability inventory: The skill integrates with the existing agent environment which includes file and service management capabilities.
  • Sanitization: Handling of Slack message content is managed by the integrated @slack/bolt dependency and internal logic in slack.ts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:39 AM