evolve

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests public web content (e.g., WebFetch to https://github.com/anthropics/claude-code/releases and https://raw.githubusercontent.com/anthropics/claude-code/main/CHANGELOG.md, plus WebSearch/WebFetch of https://docs.anthropic.com) as required research inputs and then uses those findings to plan and execute upgrades that modify files and behavior, so untrusted third‑party content can materially influence actions.