perplexityai-automation
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill provides documentation and workflow patterns for using the Perplexity AI toolkit via the Rube MCP server. This is consistent with the stated purpose of the skill and vendor branding.
- [EXTERNAL_DOWNLOADS]: The skill directs users to add a remote MCP server endpoint (https://rube.app/mcp). This is a functional requirement for the toolkit's operation and is associated with the vendor's infrastructure.
- [INDIRECT_PROMPT_INJECTION]: The skill uses dynamic tool discovery where the agent retrieves schemas and execution plans from the MCP server. This creates an interface for external data to influence agent behavior.
- Ingestion points: Data returned from the RUBE_SEARCH_TOOLS command.
- Boundary markers: Not explicitly defined in the provided instructions.
- Capability inventory: The skill utilizes RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH for task execution.
- Sanitization: The instructions recommend adhering to the returned tool schemas and field names.
- [NO_CODE]: The skill contains only instructional markdown and configuration, with no executable scripts or binaries included.
Audit Metadata