google-ads
Query, audit, and optimize Google Ads campaigns. Use an attached browser or the Google Ads API for campaign, keyword, budget, conversion-tracking, and wasted-spend analysis, or when the user explicitly requests a reviewed account change. Defaults to read-only reporting; account mutations require a bounded preview and action-time approval.
71
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Medium
Suggest reviewing before use
W009: Direct money access capability detected (payment gateways, crypto, banking).
What this means
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Why it was flagged
The skill documentation describes Google Ads management, which includes campaign, keyword, and budget analysis, as well as optional account mutations (such as budget changes) through the Google Ads API or attached browser. However, the skill defaults strictly to read-only reporting and requires an explicit, user-approved bounded preview before any mutation or change can take place. Per the core rule, managing ad spend budgets is explicitly mentioned as a financial/budget action, but the instructions emphasize that it is primarily a read-only reporting and auditing tool with strict human-in-the-loop controls for changes. Evaluating whether this meets direct financial execution authority: while it touches on budget APIs, the core design and default state are read-only auditing with required human authorization steps, and it does not inherently act as an autonomous payment gateway or crypto/banking execution tool. However, because it explicitly includes budget capabilities ("Never recommend a pause, budget change, or bid change", "budget constraints"), and ad spend budget APIs fall under the Risk 1 criteria for managing ad spend budgets, let's carefully evaluate: The prompt specifically mentions "Managing Ad Spend Budgets (specifically the API to update the budget)". This skill *does* contain instructions for updating budgets via the Google Ads API once explicitly approved ("For any pause, enable, bid, budget, targeting... account mutation... Execute and verify"). Therefore, it triggers Risk 1 due to ad spend budget management capabilities.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The Google Ads skill queries campaign performance, search terms, and ads via API or browser, which ingest third-party user-submitted ad copy and search queries.
- Repository
- jdrhyne/agent-skills
- Commit
439cd3a
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.