mollie
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill implements a secure integration pattern using Apideck's official Proxy API at unify.apideck.com. By leveraging Apideck Vault for managed authentication, the skill avoids the need for hardcoded secrets or sensitive token management within the agent's instructions. All documentation and API references target verified vendor domains for Apideck and Mollie.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from the external Mollie API, creating a potential surface for indirect prompt injection. 1. Ingestion points: Native API responses from Mollie endpoints are processed through the Apideck Proxy as described in SKILL.md. 2. Boundary markers: The instructions do not define specific delimiters or instructions to treat the API response content as untrusted data. 3. Capability inventory: The skill utilizes network operations via curl to fetch external content. 4. Sanitization: No explicit validation or filtering logic for the downstream API data is implemented, relying on the agent's inherent safety protocols.
Audit Metadata