The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches web content by routing requests through Cloudflare's markdown conversion service and Jina AI's Reader API.
[DATA_EXFILTRATION]: Instructions specify sending URLs to third-party conversion services. The skill includes a proactive disclosure regarding data transparency and advises the agent to avoid fetching pages containing sensitive authentication tokens in the URL.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by design, as it ingests content from untrusted external websites.
Ingestion points: Content retrieved from external URLs via markdown conversion services as described in SKILL.md.
Boundary markers: Not specified; the instructions do not define specific delimiters for the fetched content when presented to the agent.
Capability inventory: The agent uses the WebFetch tool to acquire data and is intended to parse and extract information from the resulting Markdown.
Sanitization: No explicit instructions for sanitizing or escaping the fetched content are provided, though the use of conversion services naturally strips some HTML-based vectors.

web-fetch-as-markdown