The Agent Skills Directory

[SAFE]: The skill is a set of guidelines and code snippets for red-teaming and security auditing. It focuses on detecting 'mass assignment' vulnerabilities where an application blindly accepts extra data fields in API requests.
[COMMAND_EXECUTION]: The skill provides example curl commands and a bash loop for security testing. These commands are intended for the user to run against targets they have permission to test and do not represent autonomous malicious behavior.
[DATA_EXFILTRATION]: There is no evidence of data exfiltration. The network operations (via curl and requests) are directed toward an example target.com and are meant for testing API responsiveness to specific payloads.
[PROMPT_INJECTION]: No prompt injection or behavior override patterns were found. The language used is purely instructional and technical.
[REMOTE_CODE_EXECUTION]: The Python snippets (requests.patch, requests.post) are standard library usage for interacting with APIs and do not involve executing untrusted remote code.

hunt-mass-assignment