create-research-prompt
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a text-based workflow for prompt engineering and does not contain malicious code or external dependencies. It references a local resource 'resources/research-types.md' for additional templates.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data such as briefs and notes in Step 1. It utilizes markdown headers in Step 4 as boundary markers. The skill has no dangerous capabilities such as file system writes, shell execution, or network access. No sanitization of user input is performed. Given the skill's role as a template generator, this surface is considered safe.
Audit Metadata