The Agent Skills Directory

SAFE (SAFE): All files were examined for security threats, including prompt injection, data exfiltration, and remote code execution. No malicious patterns were detected. The skill is entirely informational, consisting of Markdown files that provide a structured workflow for academic writing coaching.\n- Indirect Prompt Injection (INFO): The skill possesses a vulnerability surface as it ingests untrusted user data (e.g., research questions and literature summaries) to generate drafts. However, since the skill has no high-privilege capabilities such as shell execution, network access, or file-writing permissions, the potential impact of an injection is negligible.

lit-writeup