untangle-area

Warn

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The loadTypeScript function in scripts/lib/common.mjs uses createRequire and load() to dynamically import a TypeScript compiler module from a path specified at runtime via the --typescript CLI argument or the TS_MODULE environment variable.
  • [COMMAND_EXECUTION]: The skill's analysis scripts (coupling.mjs, hotspots.mjs, import-graph.mjs) execute git commands (git log, git rev-parse) using node:child_process.execFileSync to extract repository metadata and history.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from a target repository, including source code files and Git history, to generate analysis reports and tickets.
  • Ingestion points: Multiple scripts in the scripts/ directory read source files and Git commit logs from the target repository.
  • Boundary markers: While the skill defines structured output formats for logs and tickets, it lacks explicit delimiters or instructions to ignore embedded prompts within the analyzed source code.
  • Capability inventory: The skill possesses file system write capabilities (writing to docs/ and tmp/) and command execution capabilities (git).
  • Sanitization: Source code is processed using the TypeScript AST API for specific metrics, but the agent is also instructed to read raw file contents for deeper analysis.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 16, 2026, 02:27 AM