slack-bot-builder
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for building applications that process external, untrusted data from Slack messages and slash commands, which is an inherent attack surface for indirect prompt injection.
- Ingestion points: Slack message payloads in
@app.messageand command bodies in@app.command(SKILL.md). - Boundary markers: The example snippets do not include specific delimiters or instructions to ignore embedded commands in the processed text.
- Capability inventory: The skill uses
say()for posting messages andclient.views_open()for interactive UI components. - Sanitization: While the code demonstrates basic truncation (
[:2000]) for long strings, it does not include comprehensive input sanitization or escaping logic.
Audit Metadata