create-research-prompt
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a comprehensive methodology for creating research prompts without requiring elevated privileges or external network access.
- [PROMPT_INJECTION]: The skill uses instructional markers like 'CRITICAL' to prioritize workflow steps. These are benign and do not attempt to override the underlying agent's safety protocols or system instructions.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by processing untrusted user inputs such as project briefs and market research (SKILL.md). However, the risk is minimal as the skill does not utilize any high-risk tools, system commands, or external communication capabilities.
- Ingestion points: Processes user-supplied 'Project Briefs', 'Brainstorming Results', and 'Market Research' in Step 1.
- Boundary markers: None present to delimit user data from generated instructions.
- Capability inventory: No tool use or system command execution detected.
- Sanitization: No input validation or escaping mechanisms are described for the processed text.
Audit Metadata