The Agent Skills Directory

[DATA_EXFILTRATION]: The skill performs network operations to a non-whitelisted third-party domain (https://markdown.new/) to process user-provided URLs.
[INDIRECT_PROMPT_INJECTION]: The skill fetches content from external web pages and provides it to the agent, creating a surface for instructions embedded in the source material to influence the agent's behavior.
Ingestion points: External web content is ingested via the markdown.new API in scripts/fetch.sh.
Boundary markers: The fetched content is wrapped in standard YAML frontmatter delimiters (---), but there are no explicit instructions to the agent to disregard instructions found within the fetched content.
Capability inventory: The script utilizes curl for network access and standard file system utilities (jq, mv, mktemp).
Sanitization: No sanitization, validation, or content filtering is performed on the data returned from the external service before it is presented to the agent.

markdown-fetch