The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process local source code files to extract API route definitions. This data ingestion process presents an indirect prompt injection surface where malformed or malicious metadata in the source code could influence the agent's generated output.\n
Ingestion points: The scanRoutes logic in the provided scripts targets application source code directories.\n
Boundary markers: The skill does not implement explicit boundary markers or instructions to ignore embedded commands within the processed source code.\n
Capability inventory: The skill utilizes file system write operations (fs.writeFileSync) to create the API collection.\n
Sanitization: There is no evidence of sanitization or validation of the content extracted from source routes before it is interpolated into the generated .bru files.\n- [COMMAND_EXECUTION]: The TypeScript scripts included in the skill utilize the Node.js fs and path modules to perform file system operations. The logic for determining the file output path (path.join(outputDir, resource)) derives the resource component directly from the API route path without sanitizing for directory-traversal sequences (e.g., ..). This could allow the script to write files outside of the intended output directory if it processes a route path containing traversal characters.

bruno-collection-generator