The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and analyzing local source code files, which constitutes a potential attack surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: Uses Read, Glob, and Grep tools to access project files such as src/contexts/**/presentation/*.ts and schema definitions.
Boundary markers: Absent. The instructions do not define delimiters to separate untrusted file content from agent instructions.
Capability inventory: The skill is restricted to read-only operations (Read, Glob, Grep). It lacks network access, file-write capabilities, or shell execution tools, significantly limiting the impact of any potential injection.
Sanitization: No sanitization or filtering of file content is specified before the agent processes the code for validation rules.

api-validator