slack
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPERSISTENCECOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external Slack messages and direct messages, which are ingested via the
slack_listen.pydaemon andslack_read.pyscript. This content is interpolated into the agent's prompt context. Althoughsoul_engine.pyimplements boundary markers using XML tags and markdown code blocks to fence user input, the agent's high-privilege capabilities—including shell command execution (Bash) and file system access (Read/Write) as listed inskills.md—create a surface for indirect prompt injection attacks. - [PERSISTENCE]: The skill includes a macOS LaunchAgent configuration (
com.minoan.slack-daemon.plist) and associated installation scripts in thedaemon/launchddirectory. These are intended to maintain the Slack bot as a persistent background process across system restarts. - [COMMAND_EXECUTION]: The
daemon/claude_handler.pyscript executes the Claude CLI viasubprocess.run. Additionally, the skill explicitly enables theBashtool for the agent, providing the capability to execute shell commands within the host environment. - [DYNAMIC_EXECUTION]: Multiple scripts, such as
scripts/slack_channels.py,scripts/slack_post.py, andscripts/slack_users.py, utilize dynamic imports via__import__("os")to perform runtime path resolution for resolving local module locations.
Audit Metadata