mcp-github-bridge

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

• Third-party content exposure detected (high risk: 0.85). At runtime the workflow’s “CALL” step invokes mcp__github__issue_read / mcp__github__pull_request_read / mcp__github__get_file_contents, whose returned GitHub body text (authored by outside GitHub users/maintainers) is then rendered verbatim into the agent’s LLM context in “RENDER” (quoted blockquote), enabling indirect prompt injection from tool output.