acc-create-dockerignore
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- [Prompt Injection] (LOW): The skill exposes an indirect prompt injection surface by instructing the agent to process untrusted data. 1. Ingestion points: .gitignore, symfony.lock, artisan, and CI/CD configurations. 2. Boundary markers: Absent in instructions. 3. Capability inventory: None; the skill is limited to text generation and does not define subprocess calls or file-write operations. 4. Sanitization: Absent.
- [Data Exposure] (SAFE): The skill identifies sensitive files like .env and auth.json for the purpose of excluding them from Docker builds, which is a recommended security practice.
- [No Code] (SAFE): The skill consists entirely of markdown instructions and contains no executable scripts, dependencies, or network operations.
Audit Metadata