The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests data from a 'brain' knowledge base and synthesizes it into responses, creating an attack surface for instructions embedded in that data.
Ingestion points: The skill retrieves content through the search, query, get_page, list_pages, and traverse_graph tools as described in SKILL.md.
Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when handling content retrieved from the brain.
Capability inventory: The skill has extensive read access to pages, graph relationships, and timelines via the provided toolset (SKILL.md).
Sanitization: There is no evidence of sanitization, escaping, or filtering of retrieved content before it is processed by the agent to generate a synthesized answer.

query