claude-code-bash-patterns

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

• Third-party content exposure detected (high risk: 0.80). The skill includes explicit examples of using the GitHub CLI to fetch and read PR comments and other repo data (e.g., "gh api repos/owner/repo/pulls/123/comments" and "gh pr create"/"gh pr comment"), which would cause the agent to ingest untrusted, user-generated content from public third-party sources as part of its workflow.