remocn-carousel

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions to execute shell commands via npx that incorporate user-provided or externally-sourced identifiers (e.g., npx shadcn@latest add @remocn/<name>). If the <name> parameter is not validated by the agent, it could lead to command injection vulnerabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external "briefs" and fetch component data from a remote registry (remocn.dev) to drive its workflow, creating an attack surface where malicious instructions could be embedded in the input data.
  • Ingestion points: User-provided project briefs and the component catalog at https://remocn.dev/llms-components.txt.
  • Boundary markers: No explicit boundary markers or delimiters are defined to separate untrusted data from the agent's instructions.
  • Capability inventory: The skill has the ability to execute shell commands (npx), write configuration files (components.json), and modify the local project structure.
  • Sanitization: There are no instructions provided for the agent to sanitize or validate input from the briefs or the remote catalog before processing.
  • [EXTERNAL_DOWNLOADS]: The skill relies on fetching remote resources to function, including adding another skill (Remocn/remocn) and installing components from a third-party registry at remocn.dev. While these are part of the intended developer workflow, they involve the download and execution of code from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 06:55 PM