The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns or attack vectors were detected during analysis. The skill is composed entirely of static Markdown documentation and system instructions.
[NO_CODE] (LOW): The skill does not include any executable scripts, Python packages, Node.js dependencies, or binary files. It operates as a knowledge-based instruction set rather than a functional code extension.
[Indirect Prompt Injection] (INFO): Ingestion points: The skill processes user-provided financial queries. Boundary markers: No delimiters are present in the instructions. Capability inventory: The skill has zero capabilities for command execution, file system modification, or network communication. Sanitization: No sanitization of user input is performed. Because the skill lacks tool-calling or side-effect capabilities, the risk of indirect injection is negligible.

charlie