slack
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks due to its ability to ingest and process data from external Slack channels.
- Ingestion points: External Slack message content is retrieved via the
readMessagesaction defined inSKILL.md. - Boundary markers: The instructions lack explicit boundary markers or 'ignore' instructions to isolate message content from agent logic.
- Capability inventory: The skill possesses significant capabilities, including
sendMessage,editMessage,deleteMessage, andpinMessage, which could be manipulated by malicious message content. - Sanitization: There is no evidence of sanitization or validation of the text retrieved from Slack channels before it enters the agent context.
Audit Metadata