kata-ex-design-review
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Elixir codebases and review requests. Malicious content within the codebase could attempt to influence the agent's analysis or output through indirect prompt injection.
- [COMMAND_EXECUTION]: The skill allows the use of Elixir development tools and project-specific aliases. While it includes explicit instructions to inspect aliases and avoid automatic tool installation, the execution of code within a target project's context is an inherent capability that requires caution.
Audit Metadata