slack
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFE
Full Analysis
- Slack Context Interaction: The skill is designed to read and process information from Slack channels, threads, and canvases. When managing data from shared communication platforms, it is a standard security consideration to ensure the agent correctly interprets and contextualizes the external content before further action.
- High-Impact Mention Safety: It incorporates explicit checks for broad notifications such as
@channeland@here. By identifying these as high-impact actions and advising the agent to call them out before posting, the skill promotes responsible use of workspace-wide messaging. - Structured Formatting Rules: The skill uses a dedicated reference for Slack's Markdown syntax. This ensures that outgoing messages, links, and mentions are formatted correctly, maintaining the integrity and readability of the data shared back to the platform.
- Intent Routing Logic: Instructions are provided to distinguish between reading context, creating drafts, and performing direct writes. This logical separation helps ensure that actions taken by the agent align closely with the user's specific request and intent.
Audit Metadata