The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard command-line tools such as curl and xmllint to perform reconnaissance and fingerprinting on target ASP.NET applications. These tools are used to inspect response headers, check for specific file paths (e.g., trace.axd), and enumerate WCF services. These operations are consistent with the skill's stated purpose of security assessment.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, specifically HTTP response bodies and headers from target websites. This data is parsed using regular expressions and scripts to identify framework versions and ViewState configurations. To mitigate risks associated with processing external content, the skill includes a mandatory confirmation gate requiring the user to explicitly define the target scope and verify commands before execution.
[DYNAMIC_EXECUTION]: The skill provides a Python script template that uses the requests library to test for ViewState parser-error differentials. The agent is intended to use this template to generate and execute network requests that probe how the target application handles various malicious ViewState shapes. This execution is confined to testing the external target system.

hunt-aspnet