The Agent Skills Directory

[Prompt Injection] (SAFE): The skill contains only informational text and code examples without any instructions intended to bypass safety guidelines or override agent behavior.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or suspicious network exfiltration patterns were detected.
[Obfuscation] (SAFE): All content is provided in human-readable markdown with no hidden encoding, zero-width characters, or homoglyphs.
[Remote Code Execution] (SAFE): No remote scripts are downloaded or executed; the code example is illustrative.
[Indirect Prompt Injection] (SAFE): As a documentation-only resource, the skill does not implement active data ingestion from untrusted sources.

webdriver