ci-cd-pipeline-builder

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local shell commands to execute Python scripts provided within its directory. It runs scripts/stack_detector.py to scan the repository and scripts/pipeline_generator.py to output configuration files. This is a core part of its functionality but involves direct interaction with the host environment's shell.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its reliance on parsing untrusted repository content to generate logic.
  • Ingestion points: Data enters the skill's context from any file in the repository being analyzed by scripts/stack_detector.py (e.g., package.json, requirements.txt, or custom scripts).
  • Boundary markers: There are no documented delimiters or instructions to ignore potential malicious content embedded within the files being scanned.
  • Capability inventory: The skill can create and modify CI/CD configuration files (like .github/workflows/ci.yml), which are automatically executed by CI providers upon push, potentially leading to the introduction of malicious steps if the generator is deceived.
  • Sanitization: The skill does not explicitly mention sanitizing or validating repository metadata before interpolating it into the generated YAML templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — ci-cd-pipeline-builder