The Agent Skills Directory

[SAFE]: The skill consists exclusively of markdown documentation, prompt templates, and instructional guides. No scripts, binaries, or executable code of any kind are included.
[SAFE]: No hardcoded credentials, sensitive file paths, or network-enabled commands (such as curl or wget) were found across the skill files.
[SAFE]: While the skill is designed to process untrusted user input to generate prompts, it lacks any functional capabilities such as shell execution, file system access, or network communication. Consequently, there is no actionable risk associated with indirect prompt injection in this context.
Ingestion points: User-provided context and requirements gathered during the workflow described in SKILL.md.
Boundary markers: Use of Markdown headers and template tags in SKILL.md and references/prompt-patterns.md.
Capability inventory: None (the skill defines no tools or executable scripts).
Sanitization: No explicit sanitization or filtering of user-provided input is implemented.

magic-prompt-generator