The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes external text sources such as outlines and transcripts to generate lesson content. While this ingestion of user-provided data presents a surface for indirect prompt injection, the impact is low as the skill's capabilities are limited to generating text output.
Ingestion points: The skill reads voice-profile.md from the project root or .claude/ directory, and accepts user-provided source files and lesson topics.
Boundary markers: No specific delimiters or safety instructions are used to distinguish the source content from the skill's operational instructions.
Capability inventory: The skill is restricted to text generation (HTML/Markdown). It cannot execute shell commands, perform network operations, or write to the file system.
Sanitization: The skill does not perform validation or sanitization of the ingested text.
[NO_CODE]: The skill consists entirely of instructional Markdown files and does not include any executable scripts, binaries, or configuration files that trigger automated code execution.
[SAFE]: All identified behaviors, including reading local configuration files for voice settings and enforcing writing constraints, are consistent with the skill's stated purpose and present no security risk to the user's environment.

lesson-writer