firecrawl-dashboard-reporting
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external web dashboards, creating a potential surface for indirect prompt injection.
- Ingestion points: External dashboard URLs defined in the Onboarding Interview and Collection Plan (SKILL.md).
- Boundary markers: Absent; there are no specific instructions or delimiters to isolate dashboard content from the agent's internal instructions.
- Capability inventory: The skill can interact with UIs (click, scroll), extract text/labels, and generate formatted reports based on the findings.
- Sanitization: Absent; the instructions do not specify any validation or sanitization of the extracted content before interpolation into the final report.
Audit Metadata