The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill relies on the npx aurochs command to download and execute the aurochs package from the npm registry during use. This pattern involves executing unversioned code from an external source at runtime.
[COMMAND_EXECUTION]: The core functionality of the skill is provided by executing shell commands to interact with the aurochs CLI for inspecting, building, and patching Office documents.
[PROMPT_INJECTION]: The skill provides capabilities to extract text and data from PPTX, DOCX, and XLSX files, which creates a surface for Indirect Prompt Injection. Maliciously crafted documents could contain instructions designed to manipulate the agent's behavior.
Ingestion points: Untrusted data enters the agent context via the aurochs [type] extract and aurochs [type] show commands.
Boundary markers: The instructions do not define delimiters or warnings to ensure the agent ignores instructions found within the document content.
Capability inventory: The skill enables reading local files and writing/modifying them via build and patch operations.
Sanitization: There is no evidence of sanitization or validation of the text extracted from documents before it is processed by the agent.

aurochs-office