The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, which constitutes an attack surface for indirect prompt injection.
Ingestion points: The extract_content function in scripts/pptx_utils.py and SKILL.md reads text, notes, and shape data from user-provided .pptx files. Additionally, the markdown_to_presentation function processes arbitrary markdown strings.
Boundary markers: The documentation and implementation do not specify the use of delimiters or 'ignore' markers to prevent the agent from executing instructions found within the presentation content.
Capability inventory: The skill possesses capabilities to read and write files to the local file system using the python-pptx library (e.g., prs.save()).
Sanitization: There is no evidence of sanitization, filtering, or validation of the extracted text before it is returned to the agent's context, allowing potentially malicious instructions to be interpreted as legitimate directives.

pptx