The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources and stored knowledge without utilizing boundary markers or sanitization, creating a surface for potential injection attacks.
Ingestion points: Data retrieved through the WebSearch tool and existing content fetched via qdrant-find as described in SKILL.md.
Boundary markers: The instructions do not define delimiters or specific markers to isolate untrusted external content from the agent's internal reasoning.
Capability inventory: The skill utilizes qdrant-store for writing findings, qdrant-find for reading stored data, and WebSearch for external information retrieval.
Sanitization: There are no instructions provided for validating, filtering, or sanitizing the content retrieved from external searches before it is processed or stored.

research-patterns