seo-project-setup
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection because it processes external data such as Google Search Console CSV exports and project strategy documents.
- Ingestion points: The agent is instructed to read files from a local workspace folder, including queries and pages data from
gsc/and other text-based strategy notes. - Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within these ingested files.
- Capability inventory: The skill can perform file system operations (creating directories and writing README files) and utilize OpenSEO MCP tools like
get_search_console_performanceandlist_projects. - Sanitization: No content validation or sanitization of the external data is performed before processing.
- Note: As this ingestion is central to the skill's primary purpose for SEO analysis, and no adversarial intent is present, the risk is negligible.
- [SAFE]: The use of the OpenSEO MCP and its associated tools is consistent with the skill's stated purpose and is authored by a vendor associated with the OpenSEO ecosystem.
Audit Metadata