agent-slackbot
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
agent-messengerNode.js package from the npm registry to provide theagent-slackbotCLI functionality. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through its interaction with external Slack data.
- Ingestion points: The agent retrieves untrusted text content from Slack channels using the
message list,message get, andmessage repliescommands documented inSKILL.md. - Boundary markers: There are no instructions for the agent to use delimiters or ignore potential commands embedded within the retrieved message text.
- Capability inventory: The agent has the capability to send messages, upload/download files, and manage reactions within the workspace using the
agent-slackbottoolset. - Sanitization: The skill does not provide mechanisms or instructions for sanitizing or validating incoming message content before it is processed by the AI.
Audit Metadata