The Agent Skills Directory

Indirect Prompt Injection (LOW): The skill processes untrusted external content from PDF and image files which can contain hidden instructions targeting the LLM. Ingestion points: load_pdf and load_image methods in SKILL.md. Boundary markers: No delimiters or ignore instructions are specified for extracted text. Capability inventory: File system read and write operations via to_csv and to_excel. Sanitization: No sanitization of extracted document text is performed.
External Downloads (SAFE): The skill depends on standard packages from the official PyPI registry.

table-extractor