kogiqa-mcp-browser-automation
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation and execution of the
kogiqa-mcppackage from the npm registry using the commandnpx kogiqa-mcp@latest. - [INDIRECT_PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection because it enables the agent to ingest untrusted data from the web and use its tools to act upon it.
- Ingestion points: The
kogiqa_get_contenttool retrieves HTML and text content from any website the agent navigates to, bringing potentially malicious instructions into the agent's context. - Boundary markers: The skill documentation does not provide instructions or delimiters to help the agent distinguish between its own instructions and data retrieved from the web.
- Capability inventory: The agent is granted capabilities to perform state-changing actions on web pages, including
kogiqa_navigate,kogiqa_click, andkogiqa_type. - Sanitization: No sanitization or validation mechanisms are described for the content retrieved from external URLs before it is processed by the model.
Audit Metadata