cashflow-chart
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external financial websites, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: The skill retrieves data from
finance.yahoo.comusing Chrome snapshots and DOM extraction inSKILL.md. - Boundary markers: No specific delimiters or safety instructions are used to separate scraped web content from the agent's instructions.
- Capability inventory: The skill has access to
Bash,Write, and browser-based script execution tools. - Sanitization: The instructions do not specify sanitization or validation logic for the data extracted from the web before it is used for chart generation or text observations.
- [DYNAMIC_EXECUTION]: The skill generates and executes code at runtime to achieve its visualization goals.
- Script generation: It dynamically assembles a self-contained HTML file containing financial data and JavaScript libraries.
- Browser evaluation: It uses the
mcp__chrome-devtools__evaluate_scripttool to run JavaScript snippets in the browser to parse financial tables. - [EXTERNAL_DOWNLOADS]: The skill references external code and data sources.
- CDN references: The generated HTML file loads Chart.js and the datalabels plugin from
cdn.jsdelivr.net, a well-known and established content delivery network. - Data sources: The skill fetches financial statements and stock metrics via Yahoo Finance MCP tools and web scraping.
Audit Metadata