The Agent Skills Directory

[Prompt Injection] (SAFE): The skill follows standard instructional patterns for role-play without attempting to bypass safety filters, extract system prompts, or override core agent constraints.
[Data Exposure & Exfiltration] (SAFE): There are no hardcoded credentials, access to sensitive file paths, or network operations (such as curl or fetch) that could lead to data theft.
[Obfuscation] (SAFE): The content consists of clear, human-readable markdown files. No Base64, zero-width characters, or encoded commands were detected.
[Unverifiable Dependencies] (SAFE): The skill does not include any package manifest files (e.g., package.json, requirements.txt) and does not download or execute remote scripts.
[Indirect Prompt Injection] (LOW): The skill is designed to ingest and analyze user-provided text (the "thesis"). While it does not specify explicit boundary markers for this untrusted data, the skill's capabilities are strictly limited to text generation. It lacks the ability to write to the filesystem, execute commands, or perform network requests, which effectively mitigates the risk of a successful indirect injection attack.

the-fool