cht

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and uses content from the public, community-driven cheat.sh platform (see SKILL.md examples like "x cht python/hello"), so the agent will read and act on untrusted third-party, user-generated snippets that could contain instructions affecting subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches live content from cheat.sh (e.g., https://cheat.sh) at runtime via the cht client and injects those snippets into responses, so external content directly controls the agent's output and is a required dependency.