nanocodex-rust-agent-framework
Fail
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill documentation recommends installing the CLI by piping a remote script directly into a shell, which allows for unverified code execution on the user's system.
- Evidence:
curl -fsSL https://nanocodex.paradigm.xyz | bashinSKILL.md. - Execution method: Direct pipe to bash from a remote third-party domain.
- [INDIRECT_PROMPT_INJECTION]: The framework is designed to build agents that process external data, providing a vector for instructions embedded in that data to override agent behavior.
- Ingestion points: The
FetchUrlToolimplementation example inSKILL.mddemonstrates fetching content from arbitrary URLs for agent processing. - Capability inventory: The skill details a framework with tool execution loops, file system workspace management, and network access capabilities.
- Boundary markers: No delimiters or boundary instructions are used in the examples to isolate external content from system instructions.
- Sanitization: The provided code examples lack input validation or sanitization for content retrieved from external sources.
Recommendations
- HIGH: Downloads and executes remote code from: https://nanocodex.paradigm.xyz - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata