eval-design
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting potentially untrusted data from users and external web sources to generate experiment designs.
- Ingestion points: User-provided experimental context (Step 0 and 1) and external content retrieved via the
WebFetchtool. - Boundary markers: The instructions lack explicit delimiters or safety instructions to prevent the agent from obeying instructions embedded within the experimental data.
- Capability inventory: The skill utilizes
Bash,Write, andWebFetchtools, which could be misused if the agent is manipulated by injected content. - Sanitization: There is no evidence of input validation or sanitization for the data processed by the agent.
Audit Metadata