The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill includes instructions for automated validation of YAML threat model files in CI/CD pipelines. This represents a potential surface for indirect injection where malformed data in the threat model could influence validation results, though the included script uses safe loading practices and is restricted in scope.\n- [DYNAMIC_EXECUTION]: The provided CI/CD template includes a python execution block to perform YAML validation. This is a standard method for CI/CD scripting and is used safely here to parse local configuration files.\n- [EXTERNAL_DOWNLOADS]: The documentation references official resources such as OWASP Threat Dragon's Docker image and GitHub Actions. These are from well-known security organizations and do not present a security risk in this context.

threat-modeling