docker_hub-automation

Fail

Audited by Gen Agent Trust Hub on Feb 14, 2026

Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [Indirect Prompt Injection] (HIGH): The skill creates a significant attack surface for indirect prompt injection by combining external data ingestion with sensitive write capabilities. Ingestion points: DOCKER_HUB_GET_ORGANIZATION and DOCKER_HUB_LIST_REPOSITORIES ingest data from Docker Hub namespaces, including repository descriptions and full Markdown README content. Boundary markers: Absent; there are no instructions for the agent to treat fetched data as untrusted or to ignore embedded commands. Capability inventory: Includes high-privilege operations such as DOCKER_HUB_ADD_ORG_MEMBER (modifying access control) and DOCKER_HUB_CREATE_WEBHOOK (triggering external notifications). Sanitization: Absent; no validation or escaping of external content is specified before processing.
  • [External Downloads] (MEDIUM): The skill requires connection to a third-party MCP server at https://rube.app/mcp. This domain is not included in the list of verified trusted sources, posing a risk regarding the integrity and origin of the tool definitions.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 14, 2026, 04:43 AM