The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to search and process external project files using grep. This creates an ingestion surface for untrusted data (the contents of the files being analyzed). While the skill's primary purpose is benign code migration, the lack of explicit boundary markers or sanitization for the content being read means that maliciously crafted content in a project file could theoretically influence the agent's reasoning or output during the migration task.
Ingestion points: Project files are read using grep commands in the current working directory.
Boundary markers: None specified in the instructions.
Capability inventory: Uses grep for file system reading and provides logic for rewriting GROQ queries.
Sanitization: None specified; the skill relies on the agent's internal reasoning to filter false positives.

i18n-array-groq-query-migration