The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted external data, including source code files, requirements documents, and coverage reports (LCOV, JSON, XML). This represents a potential surface for indirect prompt injection if these files contain malicious instructions aimed at the AI agent.
Ingestion points: scripts/coverage_analyzer.py (parses coverage reports), scripts/test_generator.py (parses source code and requirements), and scripts/metrics_calculator.py (analyzes source and test code).
Boundary markers: The skill does not explicitly define boundary markers for the data it processes within the provided scripts, relying on the agent's context management.
Capability inventory: The skill utilizes local shell execution for its Python scripts as part of its core workflow (e.g., executing python scripts/test_generator.py).
Sanitization: The scripts perform structural parsing (JSON, XML, Regex) but do not explicitly sanitize content for prompt injection patterns before the agent interprets the results.
[COMMAND_EXECUTION]: The skill's workflows and instructions require the agent to execute local Python scripts provided within the skill package (test_generator.py, coverage_analyzer.py, tdd_workflow.py, etc.) to perform analysis and generation tasks. This is an intended and documented feature of the skill's operational model for assisting with development tasks.

tdd-guide