The Agent Skills Directory

[SAFE]: The skill serves as a technical reference for security auditing and does not contain malicious code, obfuscated payloads, or unauthorized exfiltration attempts targeting the agent's environment.
[COMMAND_EXECUTION]: Employs standard command-line utilities such as openssl, base64, and curl to demonstrate how to manipulate and sign tokens. These operations are intended for use against target applications during authorized security testing.
[EXTERNAL_DOWNLOADS]: Includes instructions to fetch public keys (JWKS) from target domains via curl. This is a standard and expected procedure in JWT vulnerability research.
[PROMPT_INJECTION]: The skill does not contain instructions designed to bypass agent safety filters or override system prompts. The 'Attack Patterns' described are educational and oriented toward external application testing.

jwt-attacks