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 bunx to download and run the @exercode/problem-utils package 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-problem CLI 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-problem CLI tool to validate the generated YAML schema and directory structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 09:02 AM
Security Audit — agent-trust-hub — generate-judge-contest