money-panel
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill accesses local project data stored within the
~/.smtm/directory. This directory appears to be the application's specific workspace for session and learning data. No evidence of unauthorized data transmission or access to sensitive system credentials (like SSH or AWS keys) was found. - [INDIRECT_PROMPT_INJECTION]: The skill processes external business plans and project logs, creating a potential surface for indirect injection.
- Ingestion points: Business plan Markdown files and
~/.smtm/projects/{slug}/learnings.jsonlfiles. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested plan files.
- Capability inventory: The skill orchestrates multiple sub-reviewer skills (
/money-review-*) and synthesizes their results. It does not perform direct shell execution or network operations within this file. - Sanitization: No explicit validation or sanitization of the input text is mentioned before processing.
Audit Metadata