legend-list-best-practices
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
npm view @legendapp/list version dist-tags --jsonto compare installed versions with the registry. This is a legitimate use of developer tooling targeting the vendor's official package. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to audit and modify external source code and tests provided by the user, representing an ingestion point for untrusted data.
- Ingestion points: Project source code, tests, and local files subjected to audit.
- Boundary markers: No specific delimiters or safety warnings for embedded instructions are provided.
- Capability inventory: The agent analyzes code, suggests modifications, and executes shell commands for package metadata.
- Sanitization: No explicit sanitization of external code content is defined.
Audit Metadata