xpoz-getting-started

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to ask the user to paste their API key and then shows examples that embed that key verbatim into code and environment variables, forcing the LLM to receive and output secrets directly.

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

• Third-party content exposure detected (high risk: 0.75). This skill’s required workflow can fetch and ingest outsider-authored social media content at runtime (e.g., via MCP/SDK/CLI calls like getTwitterPostsByKeywords / search_posts that return post text), which is then fed into the agent’s LLM context as readable free text.