complexity-analyzer

Warn

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the installation of global NPM packages from unverified third-party sources: @angrysky56/ast-mcp-server and code-analysis-mcp (mapped to GitHub user saiprashanths). These are individual accounts and not recognized trusted organizations, representing a supply chain safety concern.
  • [REMOTE_CODE_EXECUTION]: The skill facilitates the execution of remote code by instructing the user to download and run external command-line tools and MCP servers to perform static analysis tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted external code files for analysis.
  • Ingestion points: Code files ingested via the --file flag in the complexity-analyzer command (described in SKILL.md).
  • Boundary markers: Absent. There are no delimiters or instructions to ignore embedded prompts within the code being analyzed.
  • Capability inventory: The skill leverages Bash, Read, Write, Grep, and Glob tools, providing significant file system and shell interaction capabilities.
  • Sanitization: Absent. There is no evidence of filtering or sanitizing the content of files before they are parsed by the analyzer.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 13, 2026, 08:23 PM