The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is instructed to review the entire project workspace and fetch content from external URLs to generate a README. This creates an attack surface for indirect prompt injection.
Ingestion points: Reads all files in the project workspace and content from four external GitHub URLs.
Boundary markers: None identified; there are no specific delimiters or instructions to ignore embedded commands in the source files.
Capability inventory: The skill is expected to perform file-writing operations to create the README.md.
Sanitization: None identified.
[EXTERNAL_DOWNLOADS]: The skill fetches Markdown files from external repositories to use as inspiration for structure and tone.
Evidence: Fetches from raw.githubusercontent.com/Azure-Samples/serverless-chat-langchainjs/refs/heads/main/README.md, raw.githubusercontent.com/Azure-Samples/serverless-recipes-javascript/refs/heads/main/README.md, raw.githubusercontent.com/sinedied/run-on-output/refs/heads/main/README.md, and raw.githubusercontent.com/sinedied/smoke/refs/heads/main/README.md.
Note: References to the Azure-Samples organization are for well-known documentation examples.

create-readme