The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external and potentially untrusted sources, creating a surface for indirect prompt injection attacks.
Ingestion points: Data is ingested via enrich_company, enrich_person, and search_resources (which can access external URLs and uploaded documents), as well as list_findings (which pulls from meeting transcripts and conversation notes).
Boundary markers: The instructions do not explicitly mandate the use of delimiters or 'ignore embedded instructions' warnings when processing the retrieved text for inclusion in the one-pager.
Capability inventory: The skill possesses the capability to write files to the local filesystem (.octave-one-pagers/ directory) and trigger the opening of the default web browser.
Sanitization: There is no mention of sanitization or escaping of external content before it is interpolated into the generated HTML structure.

one-pager