Contentful Automation

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (MEDIUM): The skill creates a surface for indirect attacks by processing external content from Contentful.
  • Ingestion points: Space names and metadata are retrieved via CONTENTFUL_LIST_SPACES and CONTENTFUL_GET_SPACE (SKILL.md).
  • Boundary markers: No delimiters or explicit instructions are provided to the agent to treat CMS metadata as untrusted data rather than instructions.
  • Capability inventory: The skill has write access via CONTENTFUL_UPDATE_SPACE, which allows the agent to modify CMS state based on potentially poisoned input.
  • Sanitization: There is no evidence of input validation or sanitization for the data retrieved from the CMS.
  • External Dependency (LOW): The skill requires the configuration of an external MCP server located at https://rube.app/mcp. While this is the intended infrastructure, it constitutes a dependency on an external, non-whitelisted domain.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 08:20 AM