The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from untrusted external sources (local project files such as package.json, pyproject.toml, and source code) to generate documentation. While these files could theoretically contain instructions designed to influence the agent's behavior during the generation process, the risk is restricted to the content of the generated README file.
Ingestion points: Reads various project configuration and source files using Read, Glob, and Grep tools as described in SKILL.md.
Boundary markers: None explicitly mentioned in the instructions to separate untrusted file content from generation logic.
Capability inventory: The skill utilizes Read, Glob, Grep, and Write tools to perform its tasks.
Sanitization: No explicit sanitization or validation of the ingested file content is performed before interpolation into the README structure.

readme-generator