The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it is designed to ingest and process untrusted data from a software repository (source code, configuration files, and manifests) to generate documentation.
Ingestion points: The skill instructs the agent to read various files throughout the repository, including README.md, package.json, Dockerfile, and other source code files.
Boundary markers: The instructions do not specify the use of clear delimiters or boundary markers when the agent processes these external files.
Capability inventory: The skill utilizes file-writing capabilities to generate the CONTEXT.md file based on the analyzed content.
Sanitization: There are no explicit instructions for sanitizing or escaping content retrieved from the repository before it is summarized into the final document.
[DATA_EXPOSURE_&_EXFILTRATION]: The skill requires access to structural and configuration files (like package.json or database configs) to perform its primary function. However, it contains explicit safeguards: "NEVER expose secrets," "NEVER include secret values," and instructions to use variable placeholders (e.g., JWT_SECRET) instead of actual credentials. These instructions align with best practices for automated documentation tools.

context-documentation