dropcontact-automation
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions and documentation with no bundled scripts or executables.
- [SAFE]: External references to rube.app and composio.dev are legitimate resources for the Dropcontact automation toolkit and do not involve unauthorized data access or execution.
- [PROMPT_INJECTION]: Indirect prompt injection surface. The skill is designed to ingest and process data from external sources and remote tool schemas via the Rube MCP server. (1) Ingestion points: Remote tool schemas returned by RUBE_SEARCH_TOOLS and lead enrichment data from Dropcontact. (2) Boundary markers: Absent. (3) Capability inventory: The skill utilizes RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH, providing significant tool execution capabilities. (4) Sanitization: No explicit validation or filtering of remote content is described in the instructions.
Audit Metadata