organizze
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill performs network requests to api.organizze.com.br, the official API endpoint for the Organizze service, which is required for its intended functionality.
- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection through data ingested from the API.
- Ingestion points: The skill processes transaction descriptions, notes, and category names retrieved from the Organizze API (SKILL.md).
- Boundary markers: There are no boundary markers or instructions to the agent to disregard commands within the fetched data.
- Capability inventory: The skill has permissions to read, create, modify, and delete financial records via HTTP requests.
- Sanitization: The skill uses standard JSON parsing but lacks specific sanitization of string content to mitigate instruction injection.
Audit Metadata