The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data (external codebase content) and possesses high-privilege capabilities (Bash execution).
Ingestion points: The skill retrieves content from the local file system using Read, Grep, and Glob tools.
Boundary markers: There are no instructions provided to the agent to treat file contents as untrusted data or to ignore natural language instructions encountered within code comments or string literals.
Capability inventory: The skill has access to the Bash tool, which allows for arbitrary command execution on the host environment, as well as Read for file access.
Sanitization: The skill lacks explicit sanitization or validation of the content retrieved from the codebase before it is processed by the agent.

codebase-search