The Agent Skills Directory

[Indirect Prompt Injection] (HIGH): The skill's primary function is to process and generate technical documentation and configurations, which constitutes a major ingestion point for untrusted data.
Ingestion points: Technical documentation, API specifications, and configuration files matching the trigger patterns.
Boundary markers: Absent. The skill does not define delimiters to separate user data from system instructions.
Capability inventory: High-privilege tools are enabled, including Bash, Write, Edit, and Read (defined in allowed-tools).
Sanitization: Absent. There is no mention of filtering or validating input before it influences tool usage.
[Command Execution] (MEDIUM): The skill requests access to the Bash tool. In the context of an agent designed to 'generate production-ready configurations' and 'validate outputs,' this provides an execution path for shell commands derived from potentially malicious inputs (Category 8 linkage).

configuration-reference-generator