core-web-vitals
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data retrieved from external tools (Search Console and Google Analytics APIs) that could potentially contain malicious instructions.
- Ingestion points: Data enters the agent's context through output from the
get_core_web_vitals,query_top_pages, andget_blended_landing_pagestools as described in SKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded content are used when interpolating tool output into the final report.
- Capability inventory: The skill is restricted to data analysis and reporting; it does not utilize any tools for subprocess execution, file system writes, or network operations to arbitrary domains.
- Sanitization: There is no evidence of sanitization or validation of strings returned by the external APIs before they are included in the markdown output.
Audit Metadata