The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to manage and interpret data from a graph system containing 'vimarshas' (inquiry nodes), which may include content from untrusted external sources.
Ingestion points: The skill uses iskron_search and iskron_look to retrieve nodes and relationship data from the graph environment as described in SKILL.md.
Boundary markers: There are no specific instructions or boundary delimiters mentioned to isolate data content from agent instructions during retrieval.
Capability inventory: The skill possesses the capability to modify the environment by creating or updating nodes and links via iskron_update and iskron_arrow tool calls.
Sanitization: The instructions do not define any validation or sanitization routines for the content of the nodes before the agent processes them for lifecycle management or summarization.

inquiry