honeybadger-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [External Downloads] (LOW): The skill directs users to add an external MCP server at
https://rube.app/mcp. This domain is not listed as a trusted source in the analyzer's configuration. - [Remote Code Execution] (LOW): The skill documentation describes the use of
RUBE_REMOTE_WORKBENCHandRUBE_MULTI_EXECUTE_TOOL, which allow for the execution of remote logic via the Composio platform. This is the primary intended functionality of the skill. - [Prompt Injection] (LOW): The skill exhibits a surface for indirect prompt injection as it executes tools based on schemas retrieved dynamically from a remote server. Evidence Chain: 1. Ingestion points: Output from
RUBE_SEARCH_TOOLS. 2. Boundary markers: None specified in the documentation. 3. Capability inventory:RUBE_MULTI_EXECUTE_TOOLandRUBE_REMOTE_WORKBENCHprovide execution capabilities. 4. Sanitization: No sanitization logic described for tool schemas.
Audit Metadata