The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or data exfiltration attempts were detected. The skill's content is entirely focused on structured software engineering methodologies.
[COMMAND_EXECUTION]: The skill defines tools such as Grep and symbol searchers (find_symbol, get_symbols_overview) for interacting with a local codebase. These are appropriate for the stated purpose of code analysis and debugging.
[INDIRECT_PROMPT_INJECTION]: The skill inherently processes untrusted data (the user's codebase). To mitigate potential issues, it mandates evidence-based reporting with specific file and line citations, as well as explicit confidence levels to prevent the agent from blindly following instructions found within the code being analyzed.

investigation-patterns