google-ads-connect

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the installation of the google-ads Python package, which is the official client library provided by Google for API interaction.
  • [COMMAND_EXECUTION]: The skill executes several local Python scripts included in the skill package (oauth_setup.py, audit.py, mutate.py) to manage authentication flows, fetch performance metrics, and execute account mutations.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and analyzes untrusted data from Google Ads Search Term reports. This risk is effectively managed through a mandatory human-in-the-loop confirmation step before any changes are finalized.
  • Ingestion points: Data is ingested from the Google Ads API (specifically Search Term and Keyword performance reports) via scripts/audit.py.
  • Boundary markers: No explicit delimiters are specified in the instructions for isolating ingested search term data during analysis.
  • Capability inventory: The skill includes a mutation script (scripts/mutate.py) capable of pausing keywords, adding negative keywords, and adjusting bids.
  • Sanitization: The skill includes a mandatory confirmation prompt ("Confirm?") before executing any mutation commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 06:53 PM
Security Audit — agent-trust-hub — google-ads-connect