money-finance
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from multiple external sources including revenue platforms (Stripe, Shopify, App Store) and local project files.
- Ingestion points: Reads project profiles from
~/.smtm/projects/{slug}/profile.jsonand fetches daily revenue data from external API dashboards. - Boundary markers: The skill instructions do not specify any delimiters or safety markers to differentiate between instructions and the data being processed.
- Capability inventory: No file writing, arbitrary command execution, or dangerous subprocess capabilities were identified within the skill's instructions.
- Sanitization: There are no explicit instructions for the agent to sanitize or ignore potentially malicious instructions embedded in the financial data or project profiles.
Audit Metadata