loop-architect

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess calls to interact with AI model CLIs and execute verification scripts.
  • Evidence: The looper.py script and run-loop.py template utilize subprocess.run to call tools like kiro-cli, claude, and ollama, as well as user-defined programmatic checks.
  • Security Control: The skill strictly mandates the use of argument arrays (argv) rather than shell strings for all command executions to prevent shell injection vulnerabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a defined surface for indirect prompt injection as it processes data from external files and model outputs to drive workflow logic.
  • Ingestion points: process-notes.md (user input) and responses from AI council members (reviewers and judges).
  • Boundary markers: The run-loop.py script requires judges to return structured JSON within markdown fences to isolate the verdict from conversational text.
  • Capability inventory: The runner can execute arbitrary commands defined as 'programmatic checks' in the loop.yaml configuration and call external model CLIs.
  • Sanitization: A sophisticated 'scrub layer' is implemented in run-loop.py which scans prompts for content from sensitive files (matching globs like .env or *.key) and redacts them before sending data to models.
  • [EXTERNAL_DOWNLOADS]: The skill refers to official installation paths for CLI tools from well-known technology providers.
  • Evidence: looper.py contains probe and installation metadata for services such as Google Gemini, Anthropic Claude, and Ollama.
  • Context: These references are informational and directed toward established official repositories and domains, posing no inherent security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 11:29 AM