interview

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory workflow fetches and ingests public web content (Step 0's curl to https://api.github.com for releases and PATH 4 / Path B directives to "Use WebFetch/WebSearch") and then reads/interprets those external findings to send to MCP or use in decision-making, which exposes the agent to untrusted third-party content that could carry indirect prompt injection.