pp-meta-ads

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the meta-ads-pp-cli tool and an MCP server from the author's infrastructure.
  • Evidence: npx -y @mvanhorn/printing-press-library install meta-ads --cli-only downloads from the vendor's NPM package.
  • Evidence: go install github.com/mvanhorn/printing-press-library/library/marketing/meta-ads/cmd/meta-ads-pp-cli@latest downloads and builds from the vendor's GitHub repository.
  • [REMOTE_CODE_EXECUTION]: The installation process involves downloading and executing code from the author's public repositories and package registries.
  • Evidence: The install commands for both NPM and Go execute scripts or compile binaries from remote sources.
  • [COMMAND_EXECUTION]: The skill is designed to drive the meta-ads-pp-cli binary to perform various Meta Ads queries and system diagnostic checks.
  • Evidence: The skill defines subcommands such as fatigue, decay, overlap, learning, reconcile, bottleneck, stale, and inventory that execute the CLI tool.
  • [DATA_EXFILTRATION]: The CLI includes a functional feature to deliver output to a remote webhook as part of its standard reporting capabilities.
  • Evidence: The --deliver webhook:<url> flag allows the agent to POST command results to a user-provided external endpoint.
  • [SAFE]: All identified external resources, including GitHub repositories and NPM packages, are associated with the author's infrastructure ('mvanhorn') and represent expected operational procedures for a marketing analytics tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 01:00 AM
Security Audit — agent-trust-hub — pp-meta-ads