The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and extract content from arbitrary external URLs, creating a surface for indirect prompt injection attacks.
Ingestion points: External data enters the system through the url argument in scripts/fetch_url.py, which retrieves content from the public internet via direct requests, Playwright rendering, or third-party APIs.
Boundary markers: The extracted content is output directly to stdout or a file without structural delimiters or specific instructions for the agent to treat the content as untrusted data.
Capability inventory: The script has the capability to perform network requests and write files to the local system when the --output flag is used.
Sanitization: The script implements escape_markdown_text to prevent Markdown-based formatting injection, but it does not filter or sanitize linguistic instructions or malicious prompts embedded within the fetched content.

fetch-url