local-adversarial-review-gauntlet

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local binaries including git and various review adapters (Codex, Cursor, OpenCode) via subprocess.Popen. It supports environment variable overrides for binary paths (e.g., GAUNTLET_GIT_BIN), which is a standard pattern for developer tools requiring integration with locally installed software.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository content and user-provided intent strings, creating a potential surface for indirect prompt injection when these are passed to LLM adapters.
  • Ingestion points: Untrusted data is read from the repository filesystem and the --intent command-line argument in scripts/gauntlet.py.
  • Boundary markers: The build_prompt function utilizes explicit section headers to delimit untrusted content from instructions.
  • Capability inventory: The skill can execute local subprocesses and write results to the local filesystem.
  • Sanitization: While strings are interpolated, the skill mitigates risk by using detached checkouts, read-only sandboxes for supported adapters, and strict JSON schema validation on all model outputs.
  • [DYNAMIC_EXECUTION]: The supervisor script determines which binaries to invoke at runtime based on configuration and availability. It manages these processes with rigorous wall-clock deadlines and ensures that process groups and their descendants are terminated cleanly to prevent persistent resource usage.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 05:00 AM
Security Audit — agent-trust-hub — local-adversarial-review-gauntlet