generate-simplify-yaml

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The generated configuration facilitates uploading the project workspace to ChatGPT (OpenAI) as part of the code simplification workflow. This involves transmitting repository context to a well-known external AI service.- [COMMAND_EXECUTION]: The skill generates a 'simplify.yaml' configuration and provides a command, 'pnpm exec task-while simplify', to execute the simplification process using the 'task-while' package.- [PROMPT_INJECTION]: The skill defines a prompt template for analyzing and modifying the project's codebase, which introduces a surface for indirect prompt injection.
  • Ingestion points: Project metadata (project name, description) and the zipped workspace enter the context via 'template.md'.
  • Boundary markers: The prompt template in 'template.md' uses Markdown headers and structured sections to delimit instructions.
  • Capability inventory: The execution flow described in 'references/simplify-config.md' involves the tool applying generated '.diff' files using 'git apply'.
  • Sanitization: No specific sanitization or filtering of the repository content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 02:51 PM
Security Audit — agent-trust-hub — generate-simplify-yaml