Skills
skills/nickcrew/claude-ctx-plugin/code-quality-workflow/Gen Agent Trust Hub

code-quality-workflow

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection] (HIGH): The skill is highly vulnerable to indirect prompt injection as it ingests untrusted source code as primary input for analysis, review, and improvement tasks. Evidence: Found in ingestion points in analyze-code.md (Scan step), code-review.md (Review Process), and quality-improve.md (Analyze step). Capability: The skill has significant capabilities including file modification via Edit/MultiEdit and command execution via the Bash tool. Boundary Markers: There are no instructions for the agent to treat code as data only or to ignore natural language instructions embedded in comments. Sanitization: No sanitization or filtering of external content is specified.
  • [Command Execution] (MEDIUM): The skill explicitly enables the Bash tool for running external analysis tools. Evidence: Found in analyze-code.md under the Tool Coordination section. Risk: While intended for static analysis, this capability increases the potential impact of a prompt injection attack by providing a direct execution vector.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:23 AM