stock-market-dashboard
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests financial and market data from a remote API and embeds it into a generated HTML file, creating a surface for potential indirect prompt injection.
- Ingestion points: Data is fetched from multiple
app.sentisense.aiendpoints including market mood, sector tone, options radar, and news story clusters. - Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore instructions that might be embedded within the external API responses.
- Capability inventory: The skill utilizes the agent's capability to aggregate data and write it to the local file system as an HTML document.
- Sanitization: There are no explicit instructions requiring the agent to sanitize or escape the external API content before interpolating it into the final dashboard file.
Audit Metadata