paid-media-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from advertising platforms and landing pages, creating a vulnerability to indirect prompt injection.\n
- Ingestion points: Processes campaign settings, ad copy, auction insights (competitor data), and landing page content as specified in the Core Capabilities and Specialized Skills sections of
SKILL.md.\n - Boundary markers: Absent; the instructions do not define delimiters or provide warnings to the agent regarding potential instructions embedded in external advertising content.\n
- Capability inventory: Accesses external platforms via Google Ads MCP tools, API integrations, and Google Ads scripts.\n
- Sanitization: Absent; no mention of filtering or sanitizing content retrieved from external advertising environments or web pages.\n- [DYNAMIC_EXECUTION]: The skill involves the use of platform-specific automation scripts.\n
- Evidence:
SKILL.mdreferences the use of Google Ads scripts for automated data extraction, which involves executing code within a managed advertising environment.
Audit Metadata