The Agent Skills Directory

[SAFE]: The skill focuses on instructional workflows for code reading and navigation. It does not contain any patterns associated with prompt injection, credential harvesting, or unauthorized data access.- [REMOTE_CODE_EXECUTION]: No remote code execution patterns or external script downloads were detected. The skill suggests using established local command-line tools such as rg and git diff for symbol searching and diff analysis.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data in the form of repository source code (as mentioned in SKILL.md). While it lacks explicit boundary markers or sanitization instructions for this content, its capability set is focused on reading and navigation rather than execution or network transmission, presenting a standard operational risk for code-analysis tasks.

graph-guided-code-reading