The Agent Skills Directory

[SAFE]: The skill instructions define standard usage of the tabnine-context MCP server for repository exploration and code search. These operations are within the expected scope of a codebase search skill.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from remote repositories and OpenAPI specifications, representing a surface for indirect prompt injection.
Ingestion points: Data fetched via tabnine-context tools (Code search, File access, API discovery) from remote repositories.
Boundary markers: No specific delimiters or safety instructions are provided to the agent to treat external code as untrusted data.
Capability inventory: Semantic search, symbol lookup, and file content retrieval across indexed repositories.
Sanitization: No explicit sanitization or validation of the fetched codebase content is described in the skill.

codebase-search