malaysiakini

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

• Third-party content exposure detected (low risk: 0.10). The agent reads articles and search results from Malaysiakini (malaysiakini.com) via tools like malaysiakini_com__read_page and malaysiakini_com__get_en_search, which constitutes low-risk ingestion of third-party public web content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to connect a remote third-party MCP server from an unofficial service (unbrowse.ai), constituting an operational dependency with common/reputable unofficial provenance.