acquiring-skills

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to browse and clone public GitHub repositories (e.g., https://github.com/letta-ai/skills and https://github.com/anthropics/skills) and to read SKILL.md, README, and scripts from those repositories, which are public, user-contributed files the agent would ingest and interpret.