slack-bot-builder
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- PROMPT_INJECTION (SAFE): The instructions in
SKILL.mddefine a clear scope and grounding mechanism using reference files. There are no attempts to override agent safety guidelines or bypass restrictions. - DATA_EXPOSURE & EXFILTRATION (SAFE): The skill does not contain hardcoded credentials or access sensitive local files. The
validations.mdfile actually contains rules to detect and prevent hardcoded secrets in user-provided code. - EXTERNAL_DOWNLOADS & RCE (SAFE): No external packages or remote scripts are downloaded or executed. The skill operates as a knowledge-based assistant.
- OBFUSCATION (SAFE): All content is in plain text (Markdown) without any hidden characters, Base64 encoding, or URL masking.
- DYNAMIC EXECUTION (SAFE): The skill does not generate or execute code at runtime. It uses static regex patterns to provide feedback on user-submitted Slack application code.
Audit Metadata