NYC

gitlab-ci-best-practices

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection] (HIGH): The skill is designed to process and optimize GitLab CI/CD configuration files. This creates a vulnerability surface where malicious instructions in a processed file could hijack the agent's behavior.
  • Ingestion points: 'Read', 'Grep', and 'Glob' tools used on local project files.
  • Boundary markers: Absent.
  • Capability inventory: 'Bash', 'Write', and 'Edit' tools allow for command execution and file modification.
  • Sanitization: Absent.
  • [Command Execution] (MEDIUM): The 'Bash' tool is explicitly allowed, granting the agent the ability to execute shell commands. In the context of CI/CD optimization, this capability can be abused if the agent is influenced by malicious configurations.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 10:22 AM