The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to gather and synthesize external information from URLs and documents. This creates a surface for indirect prompt injection where adversarial content in external sources could attempt to influence the agent's behavior during the synthesis phase.\n
Ingestion points: Phase 1 (Gathering) instructions specifically direct the agent to identify and collect material from external URLs and document references.\n
Boundary markers: The skill lacks explicit delimiters or specific instructions for the agent to disregard instructions embedded within the gathered research material.\n
Capability inventory: The skill uses exarchos:exarchos_workflow for state updates, exarchos:exarchos_event for telemetry, and performs file system commits to the docs/ directory.\n
Sanitization: There are no specified sanitization steps or validation filters for the content retrieved from external sources before it is processed.

discover