cyrus-setup-slack

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes bash commands such as grep, printf, and cut to interact with the local configuration file ~/.cyrus/.env. These commands are used to check for existing configurations and append placeholders for Slack credentials without exposing the values to the model.
  • [SAFE]: The skill includes robust defensive instructions that prevent the agent from reading, scraping, or extracting secret tokens into its memory or conversation history. It implements a secure credential collection process where the user manually pastes sensitive information into a local file opened by a native system editor (e.g., VS Code or TextEdit), ensuring secrets remain under the user's control.
  • [REMOTE_CODE_EXECUTION]: Utilizes browser automation tools (claude-in-chrome and agent-browser) to facilitate the app creation process on api.slack.com. This includes a JavaScript eval call to programmatically populate the manifest JSON into the Slack developer portal, which is consistent with the skill's stated purpose of automating setup.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 06:23 AM