core-web-vitals
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local Python scripts (
google_client.py,dfs_client.py, andreport_publish.py) to perform diagnostic tasks. These scripts are used to fetch field data from CrUX, lab data from Lighthouse, and generate final client reports based on the findings. This is standard functionality for an SEO analysis tool.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external websites to identify performance issues, which constitutes a potential surface for indirect prompt injection.\n - Ingestion points: Audit and field data retrieved from external target URLs via diagnostic scripts.\n
- Boundary markers: No specific delimiters or boundary markers are defined in the instructions to separate external data from the agent's internal reasoning.\n
- Capability inventory: The skill has the ability to execute local scripts and write report files to the filesystem.\n
- Sanitization: The instructions do not describe sanitization or validation protocols for the content extracted from external URLs.
Audit Metadata