The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Bash to execute a local Python script, spec.py, which performs administrative tasks such as directory creation and metadata retrieval.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via the $featureName argument to create and label specification artifacts.
Ingestion points: The $featureName argument in SKILL.md is the primary entry point for external data.
Boundary markers: There are no explicit boundary markers or isolation instructions for the user-provided data within the workflow steps.
Capability inventory: The skill can execute shell commands (Bash) and perform filesystem writes via its bundled Python script.
Sanitization: The spec.py script mitigates potential directory traversal and injection by sanitizing the feature name using a restrictive regular expression (re.sub(r'[^a-z0-9]+', '-', name)).

specify-meta