The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides examples of shell commands for directory brute-forcing using tools like spray and ffuf. These are standard penetration testing tools, and their inclusion is consistent with the skill's stated purpose of security testing.
[INDIRECT_PROMPT_INJECTION]: The skill documents procedures for interacting with external API endpoints. In a real-world scenario, data returned from these endpoints is untrusted and could theoretically contain malicious instructions. However, the skill acts as a static methodology and does not include automated scripts that unsafely process these external responses, minimizing the injection risk to the agent itself.

mobile-backend