Skills
skills/mvanhorn/printing-press-library/pp-google-ads/Gen Agent Trust Hub

pp-google-ads

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the google-ads-pp-cli and google-ads-pp-mcp tools from the author's GitHub repository (github.com/mvanhorn/printing-press-library) using go install.
  • [DATA_EXFILTRATION]: Includes a --deliver webhook:<url> feature that enables the delivery of command output to any specified URL, which could facilitate data exfiltration if an agent is manipulated into using a malicious endpoint.
  • [COMMAND_EXECUTION]: Executes shell commands to interact with the Google Ads API via the provided CLI tool.
  • [PROMPT_INJECTION]: Presents a surface for indirect prompt injection by processing external data from the Google Ads API.
  • Ingestion points: API response data from commands such as customers_google_ads search in SKILL.md.
  • Boundary markers: Absent; external data is not delimited or specifically marked as untrusted.
  • Capability inventory: Comprehensive API write access, including mutate, create, and delete actions across Google Ads entities as documented in SKILL.md.
  • Sanitization: No sanitization or validation logic is defined for data received from the API before it is consumed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 08:34 AM