sales-forumscout
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a platform guide, utilizing local markdown files in the
references/directory to provide contextual information about ForumScout and API Direct features. - [EXTERNAL_DOWNLOADS]: The skill references the official API service
apidirect.ioand its associated Model Context Protocol (MCP) server. These references are for documentation and integration purposes and do not involve downloading or executing untrusted code. - [COMMAND_EXECUTION]: Code snippets for Bash and Python are included as educational recipes for users to interact with the API. There is no evidence of the agent automatically executing these commands or performing unauthorized system operations.
- [PROMPT_INJECTION]: Instructions include a feature for the agent to append new platform 'learnings' to a local file (
references/learnings.md). This is a documented knowledge-management pattern and does not represent a bypass of safety guidelines or the execution of untrusted commands.
Audit Metadata