research-decision-room
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process external research data (notes, tickets, surveys) and transform it into an interactive HTML dashboard. This architecture represents a surface for indirect prompt injection where malicious instructions embedded in research notes could influence the agent's synthesis or the generated output.
- Ingestion points: The
research_materialinput inSKILL.mdreceives external qualitative data. - Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate user-provided data from the agent's generation instructions.
- Capability inventory: The skill utilizes the
file_writecapability to emit the primaryindex.htmlartifact. - Sanitization: There is no explicit requirement for the agent to sanitize or escape HTML/JS content contained within the research material before interpolating it into the final artifact.
Audit Metadata