openrouter
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows security best practices by using placeholders for API keys and referencing legitimate OpenRouter service domains for its API endpoints.
- [NO_CODE]: No executable scripts or binary files are included in the skill; it consists solely of markdown instructions, metadata, and reference documentation.
- [INDIRECT_PROMPT_INJECTION]: The
references/directory contains files (llms-full.md,llms-small.md,llms.md,other.md) that are raw HTML/JavaScript artifacts from a web crawl. While these files are cluttered with boilerplate code and hydration data, they do not contain any instructions intended to override agent behavior or exfiltrate data. They are noted as an ingestion surface for indirect prompt injection, but the current content is benign.
Audit Metadata