The Agent Skills Directory

[SAFE]: The skill implements a legitimate configuration management workflow for application security preferences.
[SAFE]: Operations are restricted to local file system interactions within the .appsec/ directory, specifically managing config.yaml and reading findings.json.
[SAFE]: The skill does not perform any network operations, external downloads, or remote code execution.
[SAFE]: Extensive validation rules are defined for every configuration field (e.g., default_scope, minimum_severity), which prevents the injection of arbitrary values or unexpected data into the configuration file.
[SAFE]: No evidence of prompt injection, obfuscation, or privilege escalation was detected in the instructions or metadata.

config