seo-project-setup
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, including web search results, scraped website content for positioning research, and user-provided Google Search Console CSV files. This creates an indirect prompt injection surface where external data could potentially contain malicious instructions. However, the skill implements safety guardrails by requiring the agent to confirm all facts with the user before writing to the project context and instructing the agent to distinguish between source evidence and its own inferences.
- [COMMAND_EXECUTION]: The skill suggests creating a local workspace folder (e.g.,
~/SEO/) to store reports and CSV exports. While this implies file system operations, the actions are user-directed, limited to the user's home directory, and typical for a development or SEO workspace setup. - [DATA_EXFILTRATION]: The skill manages sensitive business data and integrates with Google Search Console and Google Analytics. All data operations are directed toward the 'OpenSEO' platform via dedicated MCP tools (
update_project_context,set_search_console_site). These operations are consistent with the skill's stated purpose and use-case.
Audit Metadata