error-debugging-multi-agent-review

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

• Third-party content exposure detected (high risk: 1.00). The skill's input parameters explicitly state it supports ingesting "Git repositories" as the review target (see sub-skills/input-parameters.md and SKILL.md's "Target for review: $ARGUMENTS"), which means the agent will fetch and interpret potentially public, user-generated repository content that can materially influence its actions.