The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides patterns for processing untrusted data from user queries and external tools, creating a vulnerability surface for indirect prompt injection.
Ingestion points: Data enters the agent context via the query input and retrieved_docs list in SKILL.md.
Boundary markers: Absent in the provided prompt templates.
Capability inventory: SKILL.md describes tools for web searching (tavily_search) and SQL database queries.
Sanitization: Not present in the provided templates.

agentic-rag