The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the codebase to generate documentation.
Ingestion points: The skill reads route files, codebase content, and existing documentation to extract information.
Boundary markers: No specific boundary markers or instructions to ignore embedded malicious prompts in the source data are provided in the templates.
Capability inventory: The skill primarily performs read operations on files and generates Markdown text. It does not perform network operations or execute commands (beyond what the agent platform's base environment allows for reading files).
Sanitization: No explicit sanitization or filtering of input content is mentioned.
[SAFE]: The provided templates for READMEs and API documentation include standard examples (e.g., npm install, curl, aws ecs) that are common in technical guides and do not represent malicious command execution or credential harvesting.

markdown-writer