ns-gitlab-ci-generator

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The generated GitLab CI pipeline template includes commands that source scripts and execute functions (e.g., source /deployer/deployer.sh, gcloudDockerDeploy). These components are integrated into the vendor's specific Docker images (e.g., nextstage/docker:dind-gcloud) and represent standard operational procedures for the intended CI/CD environment.
  • [CREDENTIALS_UNSAFE]: The skill implements safe credential management by explicitly instructing the agent to document only the names of sensitive variables (such as GCP_APP_KEY, ENV_BACKEND, or DB_PASSWORD) in the generated ci-cd-notes.md file, avoiding the exposure of actual secret values.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes local configuration files, including docker-compose.yml, composer.json, and package.json, to customize the pipeline (e.g., matching PHP versions or test commands). While these are external inputs, the agent uses them solely for structural configuration mapping, which is a low-risk activity within the context of generating static CI YAML files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 06:48 PM
Security Audit — agent-trust-hub — ns-gitlab-ci-generator