The Agent Skills Directory

[SAFE]: The skill instructions and curation methodology align with standard documentation maintenance practices. It focuses on auditing links and writing descriptions for well-known educational resources (such as MDN, freeCodeCamp, and javascript.info) without requesting high-risk permissions or performing suspicious actions.
[INDIRECT_PROMPT_INJECTION]: The skill processes external web content during the resource auditing phase. This represents a potential surface for indirect prompt injection if an attacker-controlled page contains malicious instructions designed to influence the agent's summary or documentation output. However, the skill lacks high-capability tools (such as arbitrary file-writing or code execution) that would enable a multi-step attack chain, and the surface is inherent to the skill's intended purpose.

resource-curator