The Agent Skills Directory

[SAFE]: The skill is designed purely for analyzing and optimizing text-based instructional content. It does not include any executable code, shell commands, or scripts. All operations are confined to the language model's text generation capabilities.
[DATA_EXFILTRATION]: No network-enabled tools (e.g., curl, wget, fetch) or data transmission patterns were found. The skill does not interact with external APIs or remote servers.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts. The skill relies entirely on its internal logic and provided reference documents.
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or sensitive credentials were found in the skill metadata or body.
[PROMPT_INJECTION]: The instructions do not contain markers designed to bypass AI safety filters or override system constraints. The use of directive language (e.g., 'CRITICAL', 'MUST') is strictly related to maintaining teaching methodology standards.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied 'course materials' and 'existing prompts' (ingestion points), it lacks the capabilities (network, file system, command execution) to act on malicious instructions that might be embedded in that data. No sanitization logic is explicitly defined for inputs, but the impact of an injection would be limited to generating incorrect text advice.
[OBFUSCATION]: All files are written in clear-text Markdown and YAML. No Base64, zero-width characters, or homoglyphs were detected.

mdf-teaching-optimizer