financial-goal-planner
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOW
Full Analysis
- Prompt Injection (SAFE): No instructions found that attempt to override system behavior or bypass safety filters. The prompts focus exclusively on the intended domain of financial planning.
- Data Exposure & Exfiltration (SAFE): No commands or code present that access local files, environment variables, or perform network requests.
- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill contains no code (Python, Node.js, or shell scripts) and does not reference any external packages or remote scripts.
- Indirect Prompt Injection (INFO): The skill processes user-provided financial goals. While it lacks delimiters for this input, the skill has no 'write' or 'execute' capabilities, meaning any potential injection in the user data cannot trigger harmful side effects beyond influencing the text generation for that specific session.
Audit Metadata