The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by ingesting data from external Google Slides presentations and performing automated write actions based on that data.
Ingestion points: The skill relies on output from the read_presentation tool in SKILL.md to identify objectIds and revisionIds.
Boundary markers: Absent; there are no instructions to the agent to treat presentation content as untrusted or to use specific delimiters.
Capability inventory: The skill utilizes multiple write capabilities including create_presentation, add_slide, insert_text_box, insert_shape, insert_image, set_text_style, and set_shape_text.
Sanitization: Absent; instructions indicate that set_shape_text replaces text directly without mentioning validation or escaping of the input content.

google-slides