moai-alfred-code-reviewer

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script (scripts/pre-review-check.sh) and uses the Bash tool to run several command-line utilities including pytest, ruff, mypy, and bandit for automated code analysis.
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8) as it is designed to ingest and analyze untrusted source code from the project environment while possessing high-privilege capabilities.
  • Ingestion points: The skill reads files from the src/ directory using the Bash tool and file system tools.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the code being analyzed and operational instructions.
  • Capability inventory: The agent is granted tools such as Bash (arbitrary command execution), Write/Edit (file modification), and WebFetch (network communication).
  • Sanitization: No sanitization, validation, or filtering of the ingested source code content is performed before it is presented to the LLM for review.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:06 AM