ethics-review-support
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily educational and instructional content designed to help users prepare research ethics applications. It provides structured steps and checklists without introducing any technical vulnerabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external documents such as research plans and feedback comments. While this creates a potential surface for indirect prompt injection if those documents were to contain malicious instructions, the skill does not grant the agent dangerous capabilities like arbitrary command execution or network exfiltration that would make such an attack impactful in this context.
- [COMMAND_EXECUTION]: The skill mentions the use of 'Bash' as an available tool for calculating character counts or generating deadline tables. This is a legitimate use case within the scope of the skill's purpose and does not include any pre-defined malicious commands.
Audit Metadata