generate-judge-contest
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
bunxto download and run the@exercode/problem-utilspackage from the NPM registry. This is the official utility package for the platform the skill is designed to support. - [COMMAND_EXECUTION]: The workflow involves executing shell commands to validate generated contest and problem files using the
exercode-problemCLI tool. These commands are restricted to validation logic. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests user-provided contest parameters to generate file content.
- Ingestion points: User-provided inputs such as contest ID, name, divisions, and concepts in
SKILL.md. - Boundary markers: Absent; the skill relies on the structured nature of the YAML output.
- Capability inventory: File system write access for contest and problem files; shell execution for validation via
bunx. - Sanitization: Relies on the
exercode-problemCLI tool to validate the generated YAML schema and directory structure.
Audit Metadata