web-design-guidelines

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to "Use WebFetch to retrieve the latest rules" and to "Fetch guidelines from the source URL above," meaning the agent will fetch and apply external web-hosted rules/output-format instructions which can alter its behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs using WebFetch at runtime to retrieve guidelines from an external source whose fetched content "contains all the rules and output format instructions" (an unspecified source URL fetched via WebFetch), meaning remote content would directly control the agent's prompts/output.