The Agent Skills Directory

[SAFE]: The skill operates by analyzing user-uploaded educational documents using standard file-reading tools (Read, Glob, Grep) to extract syllabus and question data.
[SAFE]: No network operations, data exfiltration patterns, or hardcoded credentials were detected.
[SAFE]: The skill contains no executable code, scripts, or remote dependencies, significantly reducing the attack surface.
[SAFE]: No evidence of obfuscation, malicious prompt injection, or persistence mechanisms was found.
[SAFE]: While the skill ingests external data (user-provided notes and papers), the lack of high-risk capabilities (like network access or command execution) ensures that the surface for indirect prompt injection is not exploitable in a meaningful way.

examprep-ai