The Agent Skills Directory

[SAFE]: The skill is instructional and provides structured workflows for debugging tasks. No malicious patterns were identified in the instructions or templates.\n- [SAFE]: The verification checklist in resources/checklist.md specifically requires the agent to ensure that fixes do not introduce security vulnerabilities such as SQL injection, XSS, or authentication bypasses.\n- [SAFE]: The resources/common-patterns.md file serves as a reference for developers, illustrating common bugs and their secure solutions, thereby promoting the use of safe coding practices.\n- [SAFE]: The skill defines a set of diagnostic tools (find_symbol, search_for_pattern) and standard development CLI tools (npm, pytest, bandit) for debugging purposes, all used within a legitimate development context.\n- [SAFE]: While the skill processes user input in the form of bug reports, it does so within a structured debugging protocol that focuses on reproduction and validation, minimizing the risk of indirect prompt injection.

oma-debug