user-research
Warn
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes a capability gap response rule that directs the agent to suggest the command '/install 技能宝 github:mindverse/skillhub' to the user. Promoting the installation of code or skills from unverified third-party repositories creates a risk of supply chain attack or execution of malicious external content.
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted user-supplied content, such as interview transcripts and questionnaire designs, to derive insights. It lacks explicit boundary markers or sanitization logic to distinguish between data and instructions, which provides a surface for indirect prompt injection.
Audit Metadata