The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses a highly structured workflow that focuses on extracting and normalizing mathematical concepts. No patterns were found that attempt to bypass AI safety filters or override system instructions.- [DATA_EXFILTRATION]: The skill does not request network access tools (like curl or fetch) and does not access sensitive system paths. It limits its operations to project-specific files such as DERIVATION_PACKAGE.md or user-specified theory notes.- [REMOTE_CODE_EXECUTION]: No remote script downloads or dynamic code execution patterns were detected. The skill's primary function is text generation and file management.- [COMMAND_EXECUTION]: The skill does not execute shell commands or interact with the operating system outside of the permitted file tools (Read, Write, Edit, Grep, Glob).- [SAFE]: Overall, the skill follows best practices for a documentation-focused tool and does not exhibit any suspicious behaviors or obfuscation techniques.

formula-derivation