ai-provider-cohere-sdk

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documents patterns for Retrieval-Augmented Generation (RAG) and tool use, which involves the ingestion of untrusted external data that could potentially contain malicious instructions.
  • Ingestion points: Untrusted data enters the agent context via the documents parameter in the chat() method and through tool role messages containing function results, as described in examples/tools-rag.md and reference.md.
  • Boundary markers: The skill demonstrates the use of structured objects ({ data: { ... } }) which helps the SDK maintain data boundaries, and identifies the safetyMode parameter in the API reference to help manage content safety.
  • Capability inventory: The documented patterns include network operations to the official Cohere API and the execution of tool functions.
  • Sanitization: The documentation focuses on SDK implementation patterns; it is recommended that developers implement source-level validation and sanitization when ingesting content from untrusted external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 03:56 PM
Security Audit — agent-trust-hub — ai-provider-cohere-sdk