The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch content from arbitrary URLs, creating a surface for indirect prompt injection if the agent processes malicious instructions embedded in the retrieved web text.
Ingestion points: index.py
The fetch function retrieves external data from a user-provided URL using requests.get(url).
Boundary markers: Absent. The skill returns the raw extracted text as the content field without using delimiters or providing warnings to the agent to ignore instructions within the data.
Capability inventory: index.py performs network read operations using the requests library.
Sanitization: The strip_html function in index.py removes HTML tags, scripts, and styles, but does not filter or sanitize the resulting text for natural language instructions that could influence the LLM.

Web Fetcher