The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external websites via the WebSearch tool and store it in a persistent database (qdrant-store), which presents a surface for indirect prompt injection.
Ingestion points: External content from the web enters the agent context through the results of the WebSearch tool as described in Step 2 and Step 3 of the workflow in SKILL.md.
Boundary markers: The skill does not explicitly define delimiters or instructions for the agent to ignore embedded commands within the retrieved web content.
Capability inventory: The skill utilizes WebSearch for network access, and qdrant-find and qdrant-store for reading and writing to a persistent knowledge base.
Sanitization: No specific sanitization, filtering, or validation of the external web content is mentioned prior to synthesis and storage in the Qdrant database.

web-research