skills/superdesigndev/treg/google-ads/Gen Agent Trust Hub

google-ads

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process data from the Google Ads API (e.g., via search queries), which introduces a surface for indirect prompt injection if external account data (such as campaign names or ad text) contains malicious instructions.
  • Ingestion points: Data returned from googleAds:search and searchStream calls as described in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or warnings for the agent to ignore embedded instructions in the API responses.
  • Capability inventory: The skill provides procedures for performing network-based mutations (creating campaigns, budgets, and ads) using the treg tool.
  • Sanitization: There is no mention of sanitizing or validating the content retrieved from the API before the agent processes it.
  • [SAFE]: The skill offers defensive programming patterns and best practices for the Google Ads API, specifically addressing the prevention of silent financial errors (handling currency micros) and ensuring correct resource cleanup. All external links direct to official Google developer documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 10:51 PM
Security Audit — agent-trust-hub — google-ads