google-news-seo

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands such as bash, curl, mktemp, and sed to retrieve and manage web content for auditing. It also dynamically generates and executes Python scripts to parse JSON-LD and HTML text. These operations are used for programmatic analysis of site data.
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to fetch page HTML from user-provided URLs for diagnostic purposes. These downloads are a core part of the SEO audit workflow.
  • [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by ingesting and processing untrusted external content (articles and schema). However, the use of regex-based filtering and JSON parsing instead of direct prompt interpolation serves as a functional boundary for the data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 07:37 AM