hybrid-cloud-rpc

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides templates for RPC services that ingest and process data across different silos, which creates a potential attack surface for indirect prompt injection if the processed data contains malicious instructions.
  • Ingestion points: RPC method parameters and update models, such as RpcMyThingUpdate in references/service-template.md, which ingest data from potentially untrusted sources.
  • Boundary markers: The skill does not explicitly detail the use of boundary markers or instructions to ignore embedded prompts within the ingested data.
  • Capability inventory: The services built using these templates have capabilities including database read/write operations via Django ORM (in impl.py) and cross-silo network communication via the RPC delegation layer.
  • Sanitization: The skill implements robust sanitization by using Pydantic RpcModel for strict schema validation and mandating the use of Field(repr=False) for sensitive attributes like tokens, secrets, and metadata to prevent unintentional data exposure via logging and error reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:57 PM
Security Audit — agent-trust-hub — hybrid-cloud-rpc