write-tweet

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill prompt explicitly instructs the LLM to use literal placeholders like {XAI_API_KEY} in generated curl headers (-H "Authorization: Bearer {XAI_API_KEY}"), which creates high risk of secret exfiltration since the LLM must handle and substitute the secret value verbatim in its output commands.

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

• Third-party content exposure detected (medium risk: 0.30). The write-tweet skill's required runtime workflow searches and ingests tweets from X via the X.AI Responses API and searches the web, which ingest outsider-authored free text.