The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external untrusted data by reading repository files (source code, config, schemas, routes, and tests) to verify documentation claims.
Ingestion points: Located in SKILL.md under the 'Ground first' section, which requires reading the repo's source and configuration files.
Boundary markers: No specific delimiters or instructions to ignore embedded prompts in the source data are defined.
Capability inventory: The skill has the capability to write new Markdown files to the repository and spawn child agents for text review.
Sanitization: No explicit sanitization or escaping mechanisms are described for the data read from the repository.

diataxis-docs