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_material input in SKILL.md receives 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_write capability to emit the primary index.html artifact.
  • 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
Risk Level
SAFE
Analyzed
Jun 12, 2026, 09:21 PM
Security Audit — agent-trust-hub — research-decision-room