The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes external Swift source code, creating a potential surface for indirect prompt injection if the files contain adversarial instructions.
Ingestion points: The skill uses Glob, Grep, and Read tools to scan all .swift files in the project directory (excluding standard build and dependency folders).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the content of the files as untrusted data or to ignore embedded instructions.
Capability inventory: The skill is equipped with file system exploration capabilities through Glob and Grep, and file reading via Read to perform its analysis.
Sanitization: The skill does not specify any sanitization, filtering, or validation of the code content before it is processed by the agent.

axiom-modernize