The Agent Skills Directory

[SAFE]: The skill contains instructional content and code snippets for using the RunwayML SDK in Node.js and Python. The logic follows standard API integration patterns for document management.
[SAFE]: External dependencies identified (@runwayml/sdk and runwayml) are official vendor resources belonging to the skill author, runwayml.
[DATA_EXPOSURE]: The skill includes examples for reading local files (e.g., './knowledge/product-faq.md'). This is consistent with the skill's primary purpose of uploading local knowledge base documents and does not target sensitive system paths or credentials.
[INDIRECT_PROMPT_INJECTION]: The skill describes a workflow where external document content is ingested to influence AI Avatar responses. This constitutes a standard knowledge-retrieval surface.
Ingestion points: Local file system via fs.readFileSync or Path.read_text, and HTTP request bodies in the Express.js example.
Boundary markers: None are explicitly defined in the provided code snippets to distinguish document content from system instructions.
Capability inventory: The skill uses file system tools (Read, Write, Edit) to manage local knowledge files. The resulting documents are used by the gwm1_avatars model for context.
Sanitization: No explicit sanitization or validation of the document content is demonstrated in the examples.

rw-integrate-documents