finance-personal-tax-saver
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill suggests referencing user-controlled data sources, which creates a potential surface for indirect prompt injection.\n
- Ingestion points: The
## 출처section specifies that the agent should refer to "사용자 vault 연말정산 노트" (user vault year-end settlement notes).\n - Boundary markers: There are no explicit delimiters or instructions to treat the vault content as untrusted data or to ignore embedded instructions within it.\n
- Capability inventory: Analysis of the skill reveals no subprocess calls, network operations, or file-writing capabilities, significantly mitigating the risk of a successful injection.\n
- Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the content retrieved from the user's vault.
Audit Metadata