The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions attempt to override agent behavior, bypass safety filters, or extract system prompts. The content is purely educational and instructional.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network exfiltration patterns were found. URLs used in examples (e.g., example.com, googleapis.com) are standard and benign.
[Obfuscation] (SAFE): No encoded strings, hidden characters, or homoglyphs were detected in the text or code snippets.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill references standard industry tools and libraries such as lighthouse and web-vitals. The use of npx lighthouse is a standard practice for performance auditing and is consistent with the skill's primary purpose.
[Privilege Escalation] (SAFE): No commands for escalating privileges, such as sudo or unauthorized chmod operations, are present.
[Persistence Mechanisms] (SAFE): No attempts to modify startup files, cron jobs, or system services were found.
[Indirect Prompt Injection] (SAFE): The skill does not ingest untrusted external data at runtime that would expose the agent to indirect injection attacks. It functions as a static knowledge base.
[Dynamic Execution] (SAFE): The skill provides code snippets for the user to implement but does not perform dynamic code generation or execution itself. No unsafe deserialization or runtime compilation patterns are present.

performance