acc-detect-docker-antipatterns
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [NO_CODE] (SAFE): The skill is documentation-only and contains no executable scripts or binaries.
- [DATA_EXPOSURE] (SAFE): Grep patterns are limited to project Dockerfiles and do not target sensitive system paths or secrets.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill analyzes untrusted Dockerfile content. Risk is minimal due to lack of write, execute, or network capabilities. Evidence: 1. Ingestion points: Dockerfiles and .dockerignore (SKILL.md); 2. Boundary markers: Absent; 3. Capability inventory: Read-only grep; 4. Sanitization: Absent.
Audit Metadata