third-party-integrations

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

• Third-party content exposure detected (high risk: 0.85). The required workflow instructs the agent to fetch Val Town guide pages and the docs sitemap from https://docs.val.town/... at runtime, which is public web content (outsider-authored free text) that the LLM would read and incorporate.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires fetching external guidance at runtime (e.g., https://docs.val.town/sitemap-0.xml and pages under https://docs.val.town/guides/) which will directly control the agent's integration instructions, and also mandates exposing the Val Town env-url https://www.val.town/x/HANDLE/VAL_NAME/environment-variables?key=KEY_NAME.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill explicitly lists a payment gateway under available guides ("Payments: Stripe" at SKILL.md:17) and gives actionable integration steps (help the user get credentials, test the connection, and store API keys in env vars at SKILL.md:8-10). That combination indicates the skill is specifically designed to integrate with a payment API (Stripe), which enables direct financial execution capabilities.