The Agent Skills Directory

[Prompt Injection] (SAFE): The skill contains no instructions designed to override agent behavior, bypass safety guidelines, or extract system prompts. It remains strictly focused on its educational purpose.
[Data Exposure & Exfiltration] (SAFE): There are no patterns suggesting access to sensitive system files, hardcoded credentials, or network commands to exfiltrate data.
[Obfuscation] (SAFE): All content is in plain markdown. No Base64, zero-width characters, or homoglyphs were detected.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not include any package files (package.json, requirements.txt) or commands to download and execute remote scripts.
[Indirect Prompt Injection] (INFO): The skill is designed to process untrusted user input (math/CS problems). While it lacks explicit boundary markers to separate user data from instructions, the skill has no executable capabilities, file system access, or network permissions, limiting any potential impact to the reasoning context only.
[Dynamic Execution] (SAFE): There are no instances of eval(), exec(), or runtime compilation; the skill exclusively uses static markdown templates.

problem-solver