The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze search results and data chunks from Qdrant to diagnose relevance issues, which exposes the agent to content that may contain malicious instructions.
Ingestion points: The agent is instructed to use Read and Grep tools to inspect data chunks and search results (SKILL.md, diagnosis/SKILL.md).
Boundary markers: The instructions lack specific delimiters or guidance for the agent to ignore potentially adversarial instructions embedded within the search data.
Capability inventory: The skill is configured with Read, Grep, and Glob tools for data analysis.
Sanitization: There is no requirement for the agent to sanitize or validate the content of retrieved results before evaluation.
[EXTERNAL_DOWNLOADS]: The skill recommends the installation and use of the qdrant-relevance-feedback Python package from PyPI for parameter tuning and evaluation. This is a legitimate utility within the Qdrant ecosystem for the stated purpose.

qdrant-search-quality