slack
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill allows the agent to read external data from Slack channels via the
readMessagesaction, creating a surface for indirect prompt injection attacks. - Ingestion points: External Slack message content fetched through the
readMessagesaction inSKILL.md. - Boundary markers: The skill lacks instructions for the agent to distinguish between user-generated message data and trusted system instructions.
- Capability inventory: The agent has capabilities to send, edit, and delete messages, which could be abused if the agent is manipulated by a malicious message.
- Sanitization: There are no documented steps for sanitizing or escaping the content retrieved from Slack before the agent processes it.
Audit Metadata