The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill is exposed to indirect prompt injection because it analyzes external source code.
Ingestion points: Data enters the system via the Read tool when accessing source files.
Boundary markers: No specific delimiters are used to wrap or isolate the content of the files being read.
Capability inventory: The skill has permissions to use Read and Write tools for local file access.
Sanitization: The skill does not perform any sanitization on the code content before analysis.

test-generator