The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions to override agent behavior or bypass safety filters were found in the skill definitions or reference files.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file path access, or unauthorized network operations were detected. Domain references are limited to official documentation (unpoly.com) and source repositories (github.com).
[Obfuscation] (SAFE): All provided code snippets and documentation are in plain, human-readable text without any signs of encoding or hidden characters.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill references the legitimate unpoly-rails Ruby gem and the unpoly npm package. No suspicious remote script execution patterns (e.g., piped curl-to-bash) are present.
[Indirect Prompt Injection] (SAFE): The skill functions as a documentation reference. While it processes developer-provided code snippets during interaction, it lacks high-risk capabilities like writing to files or making network requests based on that input.
[Command Execution] (SAFE): No shell commands or subprocess executions are defined within the skill.

unpoly-rails