producthunt-launch-kit

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt asks the agent to collect "any credentials" and to include gathered PRODUCT_DETAILS (including promo codes/credentials) in the Gemini request and in generated outputs (maker comment, emails, first comment), which requires echoing secret values verbatim and thus creates exfiltration risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill issues a runtime curl POST to the Gemini generation endpoint (https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GEMINI_API_KEY), which is a required dependency and returns generated text that directly controls the agent's outputs.