The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based instructions for manual or logic-based QA reviews. It does not perform any file system operations, network requests, or system modifications.- [NO_CODE]: No scripts (Python, JavaScript, Shell) or binaries are included or referenced by this skill.- [PROMPT_INJECTION]: No malicious patterns, bypass attempts, or instructions to override AI safety guidelines were detected.- [DATA_EXFILTRATION]: The skill does not contain any hardcoded credentials, sensitive file paths, or network communication tools.- [SAFE]: While the skill is designed to process external data such as code diffs and test evidence (an ingestion surface), it lacks any tool-calling capabilities (such as shell execution or file writing), preventing any potential indirect prompt injection from causing harm.

qa-review