Skills
skills/ali-master/skills/oRPC AI SDK Integration/Gen Agent Trust Hub

oRPC AI SDK Integration

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The provided code snippets demonstrate handling user-provided messages in a chat interface. This creates a surface for indirect prompt injection if malicious instructions are embedded in the message history passed to the AI model.
  • Ingestion points: SKILL.md (the messages input in the chat handler example).
  • Boundary markers: None present in the illustrative code samples.
  • Capability inventory: Interactions with generative AI models; no file system, network exfiltration, or shell execution capabilities were found.
  • Sanitization: Not featured in the integration examples.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 08:12 AM