dbt-dearman-give-fast
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed strictly of Markdown documentation and instructional prompts. There are no scripts, binaries, or configuration files that enable execution of commands, network requests, or access to the file system.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided message drafts and interpersonal scenarios. While this constitutes an attack surface for indirect prompt injection, the skill lacks any dangerous capabilities (such as shell access, file writing, or network communication) to exploit, and the instructions are limited to text analysis and drafting within the conversation context.
- Ingestion points: User-provided drafts or conflict descriptions as mentioned in
SKILL.md. - Boundary markers: None explicitly defined within the prompt text.
- Capability inventory: None. The skill does not invoke any system tools, external APIs, or executable scripts.
- Sanitization: No sanitization or escaping is performed on the user-provided input text.
Audit Metadata