peach-refactor-backend

Warn

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interpolates the user-provided [module] parameter directly into shell commands such as ls -la api/src/modules/[모듈명]/ and cat api/src/modules/[모듈명]/*.ts in SKILL.md. This poses a risk of command injection if shell metacharacters are included in the input.
  • [DATA_EXFILTRATION]: Risk of path traversal via the user-controlled module name in file access commands. An attacker could attempt to read sensitive files outside the intended scope using traversal sequences like ../../.env.
  • [PROMPT_INJECTION]: Vulnerable to indirect prompt injection.
  • Ingestion points: Local source files read from api/src/modules/[모듈명]/*.ts (SKILL.md).
  • Boundary markers: Absent; there are no instructions to ignore embedded commands or comments in the analyzed files.
  • Capability inventory: High-privilege subprocess execution including bun run build, bun test, and bun run lint:fixed.
  • Sanitization: Absent; content from external files is ingested and processed as trusted context for refactoring.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 15, 2026, 03:56 AM