Financial Tracker

Pass

Audited by Gen Agent Trust Hub on Feb 13, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes untrusted user-provided transaction descriptions (e.g., 'Log: [User Input]') to generate structured CSV logs and financial summaries.
  • Ingestion points: User input strings describing transactions (as seen in README.md and SKILL.md).
  • Boundary markers: Absent. The instructions do not define delimiters or provide 'ignore embedded instructions' warnings for the input data.
  • Capability inventory: The skill is restricted to generating text/table outputs. It contains no subprocess calls, file-write operations, or network requests.
  • Sanitization: Absent. There is no instruction to escape or validate the user-provided transaction descriptions before processing.
  • Metadata Analysis (INFO): The README.md contains a link to an external site ('afrexai-cto.github.io') for 'context packs'. While this is a commercial link, it does not represent a direct technical security threat within the scope of the skill execution.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 13, 2026, 02:54 PM