The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because its primary function is to review and design test code provided by the user, which may contain malicious instructions in comments or string literals.
Ingestion points: The agent ingests external source code using the Read, Grep, and Glob tools.
Boundary markers: The instructions do not provide explicit delimiters or guidance to treat user-provided code as untrusted data.
Capability inventory: The skill's permissions are limited to file reading and analysis; it does not request Write access or shell execution capabilities.
Sanitization: There are no instructions provided to sanitize or filter external content found within the code being analyzed.
[NO_CODE]: The skill consists entirely of markdown instructions and metadata. It does not contain any executable scripts, binaries, or instructions to download external code.

kotlin-testing-kmp