claude-config-optimizer

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 reads public third‑party content—e.g., Section 2.2 ("Fetch from GitHub" fetching anthropics/claude-code/CHANGELOG.md) and Section 13 ("site2skill Usage" which downloads arbitrary documentation URLs)—and requires the agent to interpret those files to summarize changes and drive config/migration decisions, exposing it to untrusted content that could inject instructions indirectly.