slack
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides functions to list conversations and read message history or thread replies.
- Ingestion points: Functions under
slack::conversations::*read external message content from Slack into the agent context (SKILL.md). - Boundary markers: None explicitly defined in the skill instructions to delimit untrusted Slack content.
- Capability inventory: The skill allows the agent to perform various Slack operations including posting messages, uploading files, and calling arbitrary Slack API methods via
slack::call. - Sanitization: No sanitization or validation of the retrieved Slack message content is mentioned.
- [SAFE]: The skill follows security best practices by recommending the use of environment variables (
${SLACK_BOT_TOKEN}) for credential management rather than hardcoding secrets.
Audit Metadata