Skills
skills/levnikolaevich/claude-code-skills/ln-626-dead-code-auditor/Gen Agent Trust Hub

ln-626-dead-code-auditor

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: Vulnerable to indirect prompt injection (Category 8) as it processes untrusted codebase files.
  • Ingestion points: Reads source code and project configuration files via Read, Grep, Glob, and MCP tools.
  • Boundary markers: Not specified to distinguish untrusted code content from agent instructions.
  • Capability inventory: Includes Bash for command execution, Read for file access, and Write for generating markdown reports.
  • Sanitization: No explicit evidence of sanitization or filtering of codebase content prior to processing.
  • [EXTERNAL_DOWNLOADS]: Downloads shared reference files and report templates from the author's official GitHub repository (levnikolaevich/claude-code-skills) when local files are missing.
  • [COMMAND_EXECUTION]: Utilizes the Bash tool to run static analysis tools, linters, and search patterns for code auditing purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 07:17 PM