openrouter

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the openai package and utilizes requests and langchain-openai to facilitate interaction with the OpenRouter service. These are well-known, standard libraries for AI application development.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it passes user-supplied messages to external LLM providers via OpenRouter.\n
  • Ingestion points: User prompt content within the messages parameter in SKILL.md.\n
  • Boundary markers: Not present in the provided code examples.\n
  • Capability inventory: Network communication with the official OpenRouter API (openrouter.ai).\n
  • Sanitization: No explicit input validation or filtering is implemented in the provided snippets.\n- [SAFE]: No malicious behavior, such as credential harvesting, command execution, or code obfuscation, was found. All external resources and dependencies originate from trusted or well-known services.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 11:09 AM
Security Audit — agent-trust-hub — openrouter