negative-keywords
Mine and manage negative keywords from search-term reports to stop wasted spend, and detect match-type bleed and cross-campaign conflicts. Use when a user wants to cut wasted spend, clean up search terms, build negative lists, or fix irrelevant clicks on Google or Microsoft Ads.
93%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The canonical home for this skill is negative-keywords in Synter-Media-AI/plugin
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 required workflow pulls the Google or Microsoft Ads search-term report, which contains query text typed by arbitrary outside searchers, so an outsider can get text into the feed the agent reads without the agent selecting a specific item.
- Repository
Synter-Media-AI/plugin
- Revision
040ddf8
- 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.