code-mentor
Pass
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The utility script
scripts/run_tests.pyusessubprocess.run()to execute test suites usingpytest,unittest, andjest. This functionality executes the code contained within the target files or directories provided as arguments to the script. This is an intended feature of the skill's developer-oriented toolkit. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and execute untrusted user-provided code for review and testing, which creates an attack surface where instructions embedded in the code could potentially influence the agent's behavior.
- Ingestion points: User-provided source code files and test directories are ingested and processed by scripts in the
scripts/directory, such asanalyze_code.pyandrun_tests.py. - Boundary markers: No explicit boundary markers or "ignore embedded instructions" delimiters are used when the agent processes or executes the external code content.
- Capability inventory: The skill has the capability to execute shell commands (via
subprocess.runinrun_tests.py) and read/write local files (e.g., updatingreferences/user-progress/learning_log.md). - Sanitization: The skill does not perform sanitization or sandboxing of user-provided code before it is analyzed or executed through the testing frameworks.
Audit Metadata