The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions direct the agent to execute Python scripts using relative paths: python3 ../core/scripts/scan_signals.py and python3 ../core/scripts/validate_schema.py. These scripts are used to analyze external code repositories and validate the generated strategy documents. This constitutes a command execution vector that depends on the integrity of the scripts located in the parent directory structure.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from potentially untrusted sources, including requirement models and source code files.
Ingestion points: The agent reads 需求模型.md and external code repositories provided via the <仓库路径> argument.
Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore embedded instructions within these external files.
Capability inventory: The skill has the capability to write files to the local filesystem (测试策略.md, 专项移交_...yaml) and execute shell commands (python3).
Sanitization: The skill does not define any sanitization or validation logic for the content extracted from external documents or source code comments before they are used to influence the testing strategy.

test-strategy