ci-cd-pipeline-builder

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because its core functionality involves reading and processing repository configuration files (such as package.json) to generate CI configuration.\n
  • Ingestion points: scripts/stack_detector.py and scripts/pipeline_generator.py read project manifests like package.json, pyproject.toml, and go.mod to determine build steps.\n
  • Boundary markers: The skill does not employ specific delimiters or security instructions to isolate or ignore potentially malicious content embedded within the ingested repository manifests.\n
  • Capability inventory: The skill uses Python scripts to perform local file read and write operations, and generates shell commands that are intended for use in CI/CD environments.\n
  • Sanitization: Commands extracted from project manifests (e.g., from the scripts section of package.json) are directly interpolated into the output YAML templates without sanitization or validation, though this is expected behavior for the tool's intended purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 10:46 PM
Security Audit — agent-trust-hub — ci-cd-pipeline-builder