skills/tambo-ai/tambo/cli/Gen Agent Trust Hub

cli

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill documentation encourages the use of 'npx tambo', which involves downloading and executing code from the npm registry at runtime. While the 'tambo' package is not in the explicitly trusted organization list, this is the intended and primary purpose of the skill for project management.
  • COMMAND_EXECUTION (LOW): The CLI commands allow for project initialization and file system modifications (adding components), which are standard operations for development tools.
  • PROMPT_INJECTION (LOW): The skill documentation mentions that the CLI automatically updates 'AGENTS.md'. This represents an indirect prompt injection surface where the tool's output could influence future agent behavior, though it is a standard feature for this specific tool.
  • CREDENTIALS_UNSAFE (SAFE): The examples provided use 'sk_...' as a placeholder for API keys, which is a safe practice and does not expose actual credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:21 PM