pyre-code-ml-practice

Warn

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The example code provided in the 'Adding a New Problem' section of SKILL.md demonstrates a grading mechanism using the exec() function: exec(submission_code, namespace). This function executes arbitrary Python code submitted to the grading service API, which could be exploited by a malicious user to perform unauthorized actions on the host system.
  • [EXTERNAL_DOWNLOADS]: The installation guide in SKILL.md instructs users to clone an external repository (https://github.com/whwangovo/pyre-code.git) and run a shell script (setup.sh). This involves downloading and executing third-party code from a source outside of the skill's direct control.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 11, 2026, 12:42 AM