ai-assistant-traffic
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows a well-defined analytical workflow for processing marketing data. It uses specific, restricted tool calls for data retrieval without administrative or system-level access.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies that search queries (untrusted external data) are ingested from Search Console. It proactively mitigates injection risks by instructing the agent to regex-escape these strings before they are interpolated into tool filters in Step 5. The capabilities are limited to read-only data reporting, which significantly limits the impact of any potential injection.
- [DATA_EXPOSURE_&_EXFILTRATION]: While the skill accesses property URLs and analytics data, these operations are restricted to the primary purpose of the skill (SEO analysis) and occur through authorized MCP tool interfaces. There is no evidence of unauthorized credential access or sending data to third-party domains.
Audit Metadata