trade-journal
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from broker exports which can be manipulated to influence the agent's behavior.
- Ingestion points: Data enters the agent's context through user-provided files (e.g.,
uploads/xxx.csv) processed by theanalyze_trade_journaltool as described inSKILL.md. - Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the content being parsed from the trade journals.
- Capability inventory: The skill utilizes the
analyze_trade_journaltool and generates comprehensive Markdown reports. It specifically restricts the agent from using shell-based Python execution ('Never run Python from bash'), which limits the potential impact of an injection. - Sanitization: The instructions do not specify any validation or sanitization routines for the content of the CSV or Excel files before they are analyzed and presented to the user.
Audit Metadata