The Agent Skills Directory

[SAFE]: The skill provides instructional content aimed at preventing SSRF vulnerabilities. It outlines best practices such as allowlisting, network-level controls, and DNS rebinding mitigation.
[SAFE]: No executable scripts, subprocess calls, or network operations are included in the skill. The Python code provided in the 'What Good Looks Like' section is a static example for the agent's reference, not a script to be executed.
[SAFE]: The skill does not access sensitive local files or environment variables. While it mentions the AWS metadata endpoint (169.254.169.254), it does so to identify it as a security risk for the agent to mitigate in other code, not to access it.

ssrf-check