The Agent Skills Directory

[SAFE]: The skill is entirely composed of Markdown and YAML configuration files designed to guide an AI agent through recovery testing analysis. It does not include any scripts (Python, JavaScript, Shell) or binary executables.
[SAFE]: No network-related commands (curl, wget, fetch) or remote resource downloads were detected. The skill operates purely on provided text input and local reference files.
[SAFE]: There are no signs of prompt injection or attempts to bypass AI safety guidelines. The instructions explicitly prohibit unauthorized actions, such as injecting faults or accessing production systems.
[SAFE]: No obfuscation techniques, hidden URLs, or suspicious character encoding were found in any of the files.
[SAFE]: The skill follows a principle of least privilege, explicitly instructing the agent not to call real dependencies, read credentials, or access production environments.

recovery-testing