money-review-customer
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external business plan files and history logs to perform its analysis.
- Ingestion points: The skill reads content from user-provided file paths and project-specific snapshot/learning files located in the
~/.smtm/directory. - Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the ingested plan content.
- Capability inventory: The skill performs textual analysis and generates markdown reports; it also suggests subsequent slash command invocations to the user.
- Sanitization: No validation or sanitization of the input file content is documented.
- [DATA_EXFILTRATION]: The startup sequence mentioned in the skill involves a telemetry write, which transmits data to an external endpoint.
- [COMMAND_EXECUTION]: The skill documentation describes a startup sequence that involves resolving project slugs and automatically loading various learning and growth tactic categories.
Audit Metadata