blackbox

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Blackbox CLI from official and well-known sources, specifically the npm registry (@blackboxai/cli) and the official GitHub repository (blackboxaicode/cli). These are legitimate dependencies required for the skill's primary functionality.
  • [COMMAND_EXECUTION]: The skill uses the terminal tool to invoke the blackbox CLI and standard shell utilities like git, mktemp, and gh. These operations are consistent with the skill's purpose as a coding assistant and do not show signs of malicious intent or unauthorized access.
  • [CREDENTIALS_UNSAFE]: The skill handles authentication correctly by directing the user to use the CLI's native configuration command (blackbox configure) and storing the API key in the standard local configuration path (.blackboxcli/settings.json). There are no hardcoded keys or instructions to expose secrets unsafely.
  • [PROMPT_INJECTION]: While the skill processes user-provided coding tasks that are passed to a sub-agent, it does not contain any instructions that attempt to bypass safety filters, extract system prompts, or override agent constraints. The use of single quotes in prompt examples provides a basic layer of shell argument safety.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 01:44 PM
Security Audit — agent-trust-hub — blackbox