The Agent Skills Directory

[SAFE]: The skill provides documentation and examples for a legitimate RAG workflow using Qdrant tools. No malicious instructions, obfuscation, or unauthorized access patterns were found.
[INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that ingests external data into a vector database for later retrieval, which is a standard attack surface for indirect prompt injection. * Ingestion points: Data is intended to be fetched from external sources and stored via the qdrant-store tool as described in SKILL.md. * Boundary markers: The provided patterns do not include explicit instructions for delimiting or ignoring embedded commands in retrieved content. * Capability inventory: The skill interacts with the qdrant-store and qdrant-find tools. * Sanitization: No content sanitization or validation steps are mentioned in the instructional workflow.

qdrant-patterns