tdd-test-generator

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a vulnerability to indirect prompt injection through its script generation logic.\n
  • Ingestion points: The script scripts/gen_pytest.py ingests untrusted data through command-line arguments filename and function_name via sys.argv.\n
  • Boundary markers: No delimiters or instructions are present to prevent the agent from obeying instructions embedded in the provided names.\n
  • Capability inventory: The skill has file-writing capabilities through the open().write() operation in scripts/gen_pytest.py.\n
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the input arguments before they are interpolated into the generated Python code or used in file path construction.\n- [COMMAND_EXECUTION]: The file scripts/gen_pytest.py performs dynamic code generation by assembling Python source code via string concatenation. It writes this content to the file system as a new script, which represents the creation of executable content based on runtime inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 08:37 PM
Security Audit — agent-trust-hub — tdd-test-generator