Skills
Navigate
skills/mvanhorn/printing-press-library/pp-google-ad-manager/Gen Agent Trust Hub

pp-google-ad-manager

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the google-ad-manager-pp-cli tool from the author's repository github.com/mvanhorn/printing-press-library via go install.
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute the @mvanhorn/printing-press-library package for installation purposes.
  • [DATA_EXFILTRATION]: The CLI supports a --deliver webhook:<url> argument, which allows routing tool output to any external URL, presenting a potential exfiltration vector.
  • [COMMAND_EXECUTION]: The skill involves executing a local binary google-ad-manager-pp-cli with arguments provided by the user.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Google Ad Manager API, which is an external and potentially untrusted data source. Ingestion points: API response data from Google Ad Manager. Boundary markers: Not mentioned in the instructions. Capability inventory: Includes file system writes (--deliver file), network POSTs (--deliver webhook), and inventory modification. Sanitization: Not specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 12:01 PM