Skills
skills/audn-ai/skills/audn-login/Gen Agent Trust Hub

audn-login

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes shell commands to manage MCP servers via the claude CLI. It also provides instructions for persisting the AUDN_API_TOKEN by appending it to the shell profile (~/.zshrc).
  • [EXTERNAL_DOWNLOADS]: Registers a remote MCP server definition from the vendor's official domain (https://mcp.audn.ai/mcp/audn-rn8sx).
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by including the $ARGUMENTS placeholder without boundary markers or sanitization. Ingestion points: $ARGUMENTS in SKILL.md. Boundary markers: Absent. Capability inventory: Subprocess execution via Bash (claude mcp, curl, export). Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 11:03 PM