jam-mcp-debugger

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly loads content from public jam.dev links (SKILL.md workflow: "Extract Jam links" and calls to Jam MCP tools like getDetails, getUserEvents, getConsoleLogs, getNetworkRequests, analyzeVideo, getScreenshot) and uses that user-generated/untrusted Jam content to derive repro steps and drive debugging and code-change actions, so third-party content can materially influence the agent's decisions.