slack-expert
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown without executable scripts, shell commands, or external dependencies.
- [SAFE]: The instructions explicitly promote security best practices for Slack integrations, including signature verification, secure token handling, and privacy-safe message behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process Slack events and interactions, which are untrusted external inputs. While this presents an inherent attack surface for any messaging integration, the instructions specifically mandate request verification and authentication handling to mitigate these risks.
- [METADATA_POISONING]: The metadata references a non-existent or future model (gpt-5.6-sol), but this appears to be a placeholder or specific configuration for a target environment rather than a deceptive or malicious pattern.
Audit Metadata