pp-meta-ads

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and installs the meta-ads-pp-cli and meta-ads-pp-mcp tools from the official repository of the vendor mvanhorn (github.com/mvanhorn/printing-press-library). These are trusted installations within the vendor's own namespace.\n- [COMMAND_EXECUTION]: The skill facilitates the execution of Meta Ads diagnostic commands via a local binary. All documented capabilities are explicitly read-only, focusing on data retrieval and local analysis (e.g., creative fatigue, audience overlap) rather than account modification.\n- [CREDENTIALS_SAFE]: The skill uses a standard environment variable (META_ACCESS_TOKEN) for authentication, which is a secure practice for CLI tools. It provides clear guidance on using short-lived tokens and restricted scopes (ads_read only).\n- [DATA_EXFILTRATION]: While the skill includes a --deliver webhook:<url> feature, it is presented as a standard output routing mechanism for agent workflows. The default behavior is local-only, and there are no signs of automated exfiltration of sensitive system files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:14 AM