maui-ai-debugging

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill includes commands that set/get secure-storage and fill password fields with literal secret strings (e.g., "eyJhbGc...", "pwd123") and shows examples embedding tokens/passwords directly in CLI arguments, which would require the LLM to handle and emit secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.75). The runtime workflow ingests outsider-authored free text via the app’s own UI/Blazor surfaces: maui devflow ui tree/query/property/screenshot and maui devflow webview snapshot/source read arbitrary text/DOM content from the running app (which may include user-generated or third-party content), and that readable text is then placed into the agent/LLM context.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)