marketing-paid-ads
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its automated research functionality which extracts data from third-party sources.
- Ingestion points: The skill uses
agent-browserto retrieve the text content of competitor landing pages and ad transparency centers (Meta, Google, TikTok, LinkedIn) specified inSKILL.md. - Boundary markers: There are no explicit delimiters or specific instructions to isolate the scraped content from the agent's core instructions, nor are there warnings to ignore embedded commands within the retrieved data.
- Capability inventory: The agent has the ability to read and write to the local file system (saving deliverables and screenshots) and perform network operations via browser automation.
- Sanitization: No sanitization, filtering, or validation of the external scraped content is performed before it is analyzed to generate campaign strategies.
- [EXTERNAL_DOWNLOADS]: The skill requires the
agent-browserdependency, which is fetched from the official Vercel Labs GitHub repository. This is a trusted source and the installation follows established patterns.
Audit Metadata