create-research
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process user-provided files and questions which can contain untrusted instructions.
- Ingestion points: The skill reads any file mentioned by the user in the research questions (SKILL.md, Step 1).
- Boundary markers: Absent. The instructions do not provide explicit delimiters or warnings to the sub-agents to ignore instructions embedded within the research data.
- Capability inventory: The skill uses powerful tools including
Bash,Read,Write,Grep,Glob, andAgent(for spawning parallel sub-agents). - Sanitization: No content-based sanitization or filtering is performed on the retrieved file data before analysis by the Explore agents.
Audit Metadata