blog-ki-linz

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill reads a local env file and then constructs curl POST/GET commands that include SUPABASE_SERVICE_ROLE_KEY in Authorization/headers, which requires embedding the secret value into generated commands/requests and thus risks exposing the secret verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill's STEP 2 ("Research Topic") explicitly instructs the agent to "Use WebSearch" to fetch public web content (meetups, news, startups, forums, etc.), which is untrusted/third‑party material that the agent must read and interpret to select topics and write/publish the article.