ga4-campaign-cross-reference
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a methodology for analyzing external data (GA4 behavioral data and Google Ads settings), creating an attack surface where malicious instructions embedded in those data sources could influence agent behavior.
- Ingestion points: The framework ingests GA4 reports (geographic, landing page, device data) and Google Ads configuration settings.
- Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish between its operational instructions and the potentially untrusted data it is analyzing.
- Capability inventory: The skill's capabilities are restricted to the
Readtool as defined in the YAML frontmatter ofSKILL.md. - Sanitization: There are no explicit instructions for validating, sanitizing, or escaping the external data before processing.
- [EXTERNAL_DOWNLOADS]: The
README.mdfile contains instructions for downloading the skill definition file from an external repository. - Evidence: A
curlcommand downloadsSKILL.mdfromhttps://raw.githubusercontent.com/fourteenwm/ppc-ai-skills/main/ga4-campaign-cross-reference/SKILL.md. - Note: The download source is the author's official GitHub repository, which is considered a vendor resource for this skill.
Audit Metadata