The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized exfiltration attempts were detected. The skill's instructions are consistent with its stated purpose of providing unit testing assistance.
[COMMAND_EXECUTION]: The skill requests access to the Bash tool to verify the validity of generated tests by running them. This execution is local to the user's environment and scoped to testing tasks.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its core functionality of reading and analyzing source code.
Ingestion points: Examines source code files via the Read tool.
Boundary markers: The instructions do not explicitly define delimiters or warnings to ignore embedded instructions within the code being analyzed.
Capability inventory: Uses Read, Grep, Write, and Bash tools.
Sanitization: The skill does not implement specific filtering or sanitization for external content ingested during the analysis phase.

unit-test-generator