unit-economics
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local script
infra/chart_generator.pyto generate data visualizations. This is a standard functional component for creating financial reports within the skill's defined scope. - [INDIRECT_PROMPT_INJECTION]: The skill identifies and extracts information from external, untrusted sources (SEC filings) and incorporates this content into a final HTML report deliverable.
- Ingestion points: SEC filing text retrieved during the qualitative research phase (Step 4).
- Boundary markers: None identified; instructions do not specify delimiters or warnings for the agent when processing external text.
- Capability inventory: The skill possesses the capability to write files to the local
reports/directory and execute theinfra/chart_generator.pyscript. - Sanitization: There is no explicit requirement for the agent to sanitize, escape, or validate the content extracted from SEC filings before embedding it into the HTML report template.
Audit Metadata