influencer-discovery

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to ask the user to paste API keys/codes into the chat and then embed those secrets verbatim in code/commands (e.g., XpozClient("THE_KEY_FROM_USER") and mcporter config add ... 'Authorization=Bearer {token}'), which forces the LLM to handle and output sensitive secret values directly.

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored text at runtime by querying X/Twitter and then fetching tweet text via getTwitterPostsByAuthor (MCP) / client.twitter.get_posts_by_author(..., fields: ["text", ...]) (SDK), where tweet text is freeform user/author content.