update-llms-text

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md's "Add links" workflow explicitly requires the agent to "load and analyze its source file to identify its title and determine an appropriate description," meaning the agent will fetch and interpret arbitrary public URLs (untrusted third-party content) and use that content to determine how to update llms.txt.