prepare-quarterly-business-review
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Prompt Injection] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) due to its design of ingesting untrusted data from connected tools. 1. Ingestion points: CRM, support platform, chat, and knowledge base referenced in SKILL.md. 2. Boundary markers: None. 3. Capability inventory: The skill is restricted to text generation and agenda formatting; it cannot execute code or access the filesystem. 4. Sanitization: External data is used directly in drafts without sanitization.
- [NO_CODE] (SAFE): This is a markdown-only skill with no executable scripts or external dependencies.
Audit Metadata