The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from the repository being analyzed (e.g., source code, README files) to generate the onboarding guide. This presents an indirect prompt injection surface where malicious content within the codebase could attempt to influence the agent's behavior during the generation process.
Ingestion points: Codebase files accessed via Read, Glob, and Grep (SKILL.md).
Boundary markers: The skill does not define specific delimiters or warnings to ignore embedded instructions in the files it reads.
Capability inventory: Write tool used for guide generation; Bash for git operations and opening the resulting files.
Sanitization: No specific sanitization or escaping of the ingested codebase content is described before inclusion in the HTML guide.
[COMMAND_EXECUTION]: The skill uses shell commands to open the generated HTML file automatically.
Evidence: Use of Bash(start *) and Bash(explorer.exe *) to open the saved path (SKILL.md). While these are intended for user convenience, they execute system-level commands with dynamically generated file paths.

create-onboarding-guide