The Agent Skills Directory

[DYNAMIC_EXECUTION]: The module scripts/coverage_analyzer.py uses xml.etree.ElementTree.fromstring() to parse XML-formatted coverage reports (e.g., Cobertura). According to Python's official documentation, the ElementTree library is not secure against maliciously constructed XML data. This creates a vulnerability to XML External Entity (XXE) attacks, which could allow an attacker to read local files or perform server-side request forgery (SSRF) if a user is tricked into providing a malicious coverage report.
[INDIRECT_PROMPT_INJECTION]: The skill acts as an ingestion point for untrusted external data.
Ingestion points: scripts/test_generator.py (processes requirements and user stories), scripts/coverage_analyzer.py (processes coverage reports), and scripts/tdd_workflow.py (processes source and test code).
Boundary markers: The skill lacks explicit delimiters or instructions to the agent to treat processed data as data rather than instructions, increasing the risk of the agent following instructions embedded in source code or requirements.
Capability inventory: The skill uses Python scripts to perform static analysis, test generation, and workflow guidance. These scripts are invoked via the shell by the agent.
Sanitization: No input sanitization or validation of the structural integrity of the input data is performed before processing.

tdd-guide