The Agent Skills Directory

[SAFE]: The skill instructions were audited and found to contain no malicious patterns, unauthorized network operations, or hardcoded credentials.
[PROMPT_INJECTION]: The skill evaluates external specification files and user arguments, creating a theoretical surface for indirect prompt injection where malicious content in a specification could influence agent behavior. Ingestion points: The skill reads local files defined by the FEATURE_SPEC variable and processes the $ARGUMENTS input. Boundary markers: No specific delimiters or instruction-ignore blocks are defined for the imported content. Capability inventory: The skill utilizes local file system access to read and update feature specification documents. Sanitization: Content from external sources is processed and integrated without explicit sanitization or validation routines.

clarify