research-prompt
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists solely of instructions for the AI agent to act as an interviewer and prompt crafter. It does not include any scripts, binaries, or executable commands.
- [SAFE]: No data exfiltration or credential exposure risks were found. The skill does not access sensitive files or perform network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it ingests user input to generate research prompts. However, because the skill lacks executable capabilities and the resulting prompt is intended for manual use by the user in a separate session, the risk is negligible.
- [SAFE]: No obfuscation, persistence mechanisms, or privilege escalation patterns were detected in the instructions or metadata.
Audit Metadata