docker-volumes
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill relies on user-provided inputs for configuration and command generation, creating a surface for indirect prompt injection.
- Ingestion points: The 'Required Inputs' section in SKILL.md (Type of data, Host OS, etc.).
- Boundary markers: There are no explicit delimiters or instructions to treat user data as untrusted.
- Capability inventory: The skill suggests the use of Docker CLI commands and MCP tools like docker_listVolumes and docker_inspectContainer (SKILL.md).
- Sanitization: No input sanitization or validation routines are defined in the instructions.
- [SAFE]: The skill uses official Docker documentation as references, which are trusted and legitimate technical sources.
Audit Metadata