eurouter-integration
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a documentation-focused integration guide for the vendor's service ('EUrouter'). All external references point to the vendor's official API domain (api.eurouter.ai) or well-known, trusted package registries (npm/PyPI).
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for building applications that process external user data through an AI gateway, which presents a surface for indirect injection attacks.
- Ingestion points: User messages and text inputs are processed by the Chat Completions and Embeddings endpoints described in 'SKILL.md' and 'references/endpoints.md'.
- Boundary markers: The code examples provided do not include specific prompt delimiters or instructions to the agent to ignore embedded commands within user input.
- Capability inventory: The skill's execution environment is restricted to 'Read' access via the 'allowed-tools' metadata. However, the documented API supports advanced capabilities such as 'tool_calling' and 'code_interpreter'.
- Sanitization: No explicit input validation or sanitization routines are included in the reference implementation snippets.
Audit Metadata