The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's primary function involves running a local Python utility, scripts/audit_migration_tests.py, which performs automated auditing of project source code and assets. The script accepts filesystem paths as arguments and performs recursive directory traversal.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection as it is designed to ingest and analyze external, potentially untrusted project data.
Ingestion points: The scripts/audit_migration_tests.py file reads the names and contents of all files within the user-provided --java-root and --target-root directories to perform regex-based test counting and SHA-256 asset hashing.
Boundary markers: The skill lacks explicit boundary markers or delimiters to isolate the agent from potentially malicious instructions embedded within the Java or Swift source code it analyzes.
Capability inventory: The utility script has the capability to recursively read the local file system and write a JSON audit report to a target file path if the --output argument is used.
Sanitization: There is no evidence of sanitization or validation of the ingested file content before it is processed by the hashing and regex logic.

swift-java-migration-testing