remix
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides benign development guidelines and architectural patterns for the Remix framework. It does not include any malicious commands, network exfiltration, or obfuscation techniques.
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest and act upon data from local project files, which is a standard operational surface for AI coding assistants.
- Ingestion points: The agent is directed to read files such as
AGENTS.md,package.json,tsconfig.json, and application source code. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when reading these local files.
- Capability inventory: The agent has the capability to read local files, search file content using tools like
grep, and execute application-defined test scripts. - Sanitization: While it doesn't mention input sanitization for the agent's own processing, the skill explicitly advises testing rejection and failure paths for changes involving untrusted input in the application itself.
Audit Metadata