n2n-federation
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses Python scripts (
scripts/in2n-services.py) to generate and manage systemd user services, which modifies the local system's initialization and persistence layer. - [REMOTE_CODE_EXECUTION]: Tools such as
n2n_delegateandn2n_invokeenable the agent to request execution of tasks or command-line tools on remote federated peer machines. - [DATA_EXFILTRATION]: The skill facilitates significant data movement through
n2n_replicate(transferring RAG collections between peers) andn2n_notify_phone(pushing content to mobile devices). - [PROMPT_INJECTION]: The skill processes capability inventories and knowledge base responses from remote peers, which acts as a vector for indirect prompt injection.
- Ingestion points: Remote peer capability inventories,
n2n_knowledge_queryresponses, andn2n_task_resultdata found in SKILL.md. - Boundary markers: The skill instructs the agent to treat peer information as untrusted input, though no specific technical delimiters (like XML tags) are enforced in the prompt text.
- Capability inventory: Remote task execution (
n2n_delegate), local service management (scripts/in2n-services.py), and data replication (n2n_replicate). - Sanitization: Reliance on external 'model-guard' proxies and user attribution rather than input filtering.
Audit Metadata