claude-commands

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

• Third-party content exposure detected (high risk: 0.80). The skill's examples and required command templates (e.g., the "Code Review Command" in Common Command Patterns) explicitly use shell directives like {{shell:gh pr diff {{pr_number}}}} which fetch PR diffs from GitHub (user-generated, third-party content) that the agent is expected to read and act on as part of the workflow, enabling indirect prompt injection.