The Agent Skills Directory

[PROMPT_INJECTION]: The instructions utilize role-playing definitions (e.g., 'Chief Vector Illustration Engineer') to guide the agent's creative and technical output. These are context-appropriate for a writing skill and do not contain directives to bypass safety guardrails or ignore system prompts.
[DATA_EXFILTRATION]: The skill does not use network-capable tools or commands that could exfiltrate data. There is no evidence of instructions targeting sensitive system files or credentials.
[REMOTE_CODE_EXECUTION]: No external packages or remote scripts are downloaded or executed. The skill relies on local reference files for its writing and diagramming guidelines.
[DYNAMIC_CONTEXT_INJECTION]: The skill's main instruction file and its references do not contain any dynamic context execution syntax (such as shell commands wrapped in backticks with an exclamation mark).
[OBFUSCATION]: All content, including LaTeX templates and TikZ diagram code, is provided in clear, human-readable text. No Base64, hex encoding, or zero-width character obfuscation was detected.
[SAFE]: The skill exhibits standard educational tool behavior, providing structural guidance and formatting templates without introducing security vulnerabilities or hidden malicious logic.

university-textbook