The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions in SKILL.md direct the agent to execute local Python scripts (spec_generator.py, spec_validator.py, and test_extractor.py) via the shell. These scripts are provided as part of the skill's internal toolkit to support its primary function of specification management and test generation.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent processes external data (specifications written in Markdown) which could potentially contain malicious instructions.
Ingestion points: The scripts spec_validator.py and test_extractor.py read content from files provided via command-line arguments.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when processing the files.
Capability inventory: The agent has the capability to read/write files and execute the provided Python scripts in the local environment.
Sanitization: The scripts use regular expressions for structural validation and data extraction but do not perform security-focused sanitization of the natural language content within the specifications.
[SAFE]: All included Python scripts (scripts/spec_generator.py, scripts/spec_validator.py, scripts/test_extractor.py) were audited and found to use only Python's standard library. They perform expected file I/O operations and string processing with no network access, obfuscation, or persistence mechanisms detected.

spec-driven-workflow