ln-732-cicd-generator

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection because it interpolates data extracted from local project files into executable CI/CD configuration templates.
  • Ingestion points: The skill reads metadata from package.json, pyproject.toml, and .csproj files to determine environment versions and file paths.
  • Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore or sanitize content found within these project files during extraction.
  • Capability inventory: The skill possesses the capability to create directories and write YAML configuration files to the .github/workflows/ path.
  • Sanitization: The workflow does not specify any sanitization or validation logic for the extracted strings before they are injected into the final configuration file.
  • [EXTERNAL_DOWNLOADS]: The diagram.html file fetches the Mermaid.js library from the jsDelivr CDN for workflow visualization. This uses a well-known third-party service to render documentation diagrams.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 02:43 PM