The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions and static code examples for reviewing code. It does not include scripts, executables, or network-enabled commands.- [PROMPT_INJECTION]: Analysis of the skill instructions found no attempts to bypass safety filters, override system prompts, or induce restricted behaviors.- [DATA_EXFILTRATION]: No sensitive file paths, credential markers, or non-whitelisted network operations were detected.- [INDIRECT_PROMPT_INJECTION]: Although the skill is designed to analyze external data (Pull Request code), it has no associated execution capabilities (e.g., subprocess spawning, file writes, or network requests), precluding the risk of indirect instruction execution.

skimmable