financial-planner
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data (such as income, debts, assets, and financial goals) to generate personalized financial plans.
- Ingestion points: The skill explicitly requests user context in
SKILL.md(Step 1) and utilizes these values in the prompt formulas found intemplates/prompt-main.md. - Boundary markers: The skill lacks specific delimiters or "ignore embedded instruction" warnings around user-provided data fields.
- Capability inventory: The skill is only capable of generating markdown text; no network operations, shell command execution, or file system write capabilities were detected in the provided scripts.
- Sanitization: There is no evidence of sanitization, filtering, or validation of the input data before it is processed by the agent.
Audit Metadata