Skills
skills/claudiodearaujo/izacenter/slack-bot-builder/Gen Agent Trust Hub

slack-bot-builder

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by processing untrusted data from Slack messages and interactive commands.
  • Ingestion points: Untrusted data enters the agent context through the message handler handle_hello and the slash command handler handle_ticket_command in SKILL.md.
  • Boundary markers: The provided code snippets do not implement delimiters or specific instructions to the agent to ignore instructions embedded within the Slack payloads.
  • Capability inventory: The skill grants the agent the ability to post messages to channels using the say() function and interact with the Slack UI via client.views_open().
  • Sanitization: The examples do not demonstrate input sanitization or validation before processing user-provided content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:14 AM