reviewing-code-quality

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Command Execution (SAFE): The skill executes local bash scripts (e.g., review-lint.sh, review-types.sh) stored in a platform-specific configuration directory (~/.claude/plugins/marketplaces/claude-configs/review/scripts/). These scripts are used for their primary intended purpose of code analysis and do not involve remote downloads or elevated privileges.
  • Indirect Prompt Injection (LOW): The skill identifies a surface for indirect prompt injection as it processes untrusted code files provided by users.
  • Ingestion points: Untrusted data enters the agent context through file reading and grep operations in the 'Manual Detection Patterns' section.
  • Boundary markers: Absent; there are no specific delimiters or 'ignore' instructions mentioned for the content being analyzed.
  • Capability inventory: The agent has the capability to execute shell commands (bash, grep, while read) and call other review-related skills.
  • Sanitization: Absent; the skill does not perform sanitization of the file content before it is processed by the agent's analysis logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM