skills/bcms/ai/bcms-content/Gen Agent Trust Hub

bcms-content

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a Node.js script (cli/bcms.mjs) that the agent executes to perform content operations such as creating, updating, and deleting entries.
  • [EXTERNAL_DOWNLOADS]: The skill relies on the @thebcms/client package, which is the official SDK for the BCMS platform. This is a standard dependency for the skill's functionality.
  • [DATA_EXFILTRATION]: The skill is designed to read local files and JSON data to upload them to the BCMS platform at https://app.thebcms.com. This is the core intended purpose of the skill and targets a well-known service domain.
  • [PROMPT_INJECTION]: The skill retrieves content from the BCMS API and prints it to standard output. There is a surface for indirect prompt injection where an agent might be influenced by malicious instructions stored within the content management system; however, the skill outputs structured JSON and the risk is considered low in the context of a CMS management tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 11:21 AM
Security Audit — agent-trust-hub — bcms-content