sell

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to collect and interpolate sensitive values (e.g., admin user IDs and explicitly an AI key) directly into shell command flags like --admin-ids and --ai-key, which requires the LLM to output secrets verbatim and therefore poses an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill's runtime template and workflow explicitly fetch and ingest open web content (e.g., registry endpoints via registryApiUrl like /registry.json, /check/{subdomain}, /resolve/{subdomain} and CDN-hosted modules such as https://esm.sh/* shown in the import map and template.delta.html), and the responses are parsed and used to decide routing, access control, claiming, and other actions — so untrusted third-party responses can materially change the agent's behavior.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill's generated web app loads and executes remote JavaScript at runtime (for example the import map points to React at https://esm.sh/stable/react@19.2.4), which is a required runtime dependency that will fetch and run third‑party code in users' browsers.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly built around SaaS subscription gating and repeatedly references Stripe billing (billing-mode flags, SubscriptionGate/SubscriptionPaywall components, "Stripe billing is phase 2", "Stripe checkout" etc.). Although the integration may be marked as "phase 2" / placeholder, the skill's primary purpose includes enforcing paid subscriptions and is explicitly tied to a payment gateway (Stripe). This meets the criterion of being specifically designed for financial operations (payment gateway/subscription billing), so it should be flagged.