The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities detected in the skill instructions or code snippets. All code examples use industry-standard libraries for their intended purposes.
[INDIRECT_PROMPT_INJECTION]: The skill inherently handles untrusted data through document parsing, creating an attack surface for indirect prompt injection if the output is processed by an LLM.
Ingestion points: The skill ingests data from external files using libraries such as pdf-lib, exceljs, and docxtemplater via fs.readFile and buffer loading.
Boundary markers: Code snippets do not include explicit delimiters or instructions to ignore embedded commands in the processed documents.
Capability inventory: The skill demonstrates capabilities for reading and writing local files using the fs module and processing document buffers.
Sanitization: While code snippets lack explicit sanitization, the 'Best Practices' section correctly identifies the need to sanitize filenames and validate file types as a security measure.

Processing Documents