docker-expert
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of instructional markdown and metadata, with no associated script files, binary executables, or code, which eliminates risks associated with direct malicious code execution.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Dockerfiles and build configurations, making it susceptible to instructions hidden within those files. 1. Ingestion points: Dockerfiles and multi-stage build configurations located in the workspace. 2. Boundary markers: Not defined in the instructions. 3. Capability inventory: The skill metadata in SKILL.md requests 'workspace-write' permissions, allowing the agent to modify files based on its analysis. 4. Sanitization: No explicit logic for sanitizing or escaping ingested configuration data is provided.
Audit Metadata