The Agent Skills Directory

[SAFE]: The skill is entirely instructional, providing high-level rules and reference patterns for testing best practices in Python, PHP, and JavaScript. No malicious code, command execution, or network exfiltration patterns were detected in the instructions or the associated reference files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external test code, diffs, and files provided by the user or other agents. This creates an attack surface where malicious instructions could be embedded within code comments or metadata of the files being reviewed. However, because the skill provides textual review feedback and does not possess capabilities to write to the filesystem, execute shell commands, or perform network operations, the risk of exploitation is negligible. No specific boundary markers or sanitization steps are defined for the input code.

test-guard