backlink-audit
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses specific, approved MCP tools (backlinks_research and competitors_research) to retrieve data. It does not attempt to execute arbitrary code or download external scripts.
- [SAFE]: The instructions explicitly forbid the agent from asking for Semrush API keys, instead relying on standard MCP authentication protocols, which prevents potential credential exposure.
- [SAFE]: The skill follows security best practices by including a safety gate for the Google Disavow tool, requiring explicit user request and review of evidence before suggesting high-risk actions.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the web (anchors, source URLs, and page titles) through the backlink reports. However, because the skill lacks dangerous capabilities such as file system writing, subprocess execution, or arbitrary network requests, the exploitation surface for this vector is negligible.
- [SAFE]: All external documentation and reference links point to trusted sources, including the official Semrush blog and Google Search Console support documentation.
Audit Metadata