assetfare-route
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill implements a comprehensive safety protocol that explicitly prevents the agent from requesting or storing private keys. It emphasizes that the platform never signs transactions, placing full control and verification responsibility on the user.
- [INDIRECT_PROMPT_INJECTION]: The skill fetches content from api.assetfare.dev (e.g., OpenAPI specs, capability manifests, and quotes), which could potentially deliver untrusted data into the agent's context.
- Ingestion points: SKILL.md identifies https://api.assetfare.dev/v2/openapi.json and tool-based MCP endpoints as external data sources.
- Boundary markers: While explicit delimiters for API responses are not provided, the instructions include a 'Safety boundary' and detailed verification checks for the agent to follow.
- Capability inventory: The skill is limited to information retrieval and prepopulating unsigned transaction data; it has no autonomous execution or signing privileges.
- Sanitization: The manual verification process for payload_sha256, destination addresses, and assets acts as a critical sanitization step through human oversight.
Audit Metadata