autodev

Fail

Audited by Snyk on Aug 25, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.80). The skill asks the user for a "verify" command and other freeform settings and then echoes those values verbatim into generated /goal lines, into a state.json file, and runs the command, so any user-supplied secret (API key, token, password) included in those values would be output or executed by the agent.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). autodev 스킬의 런타임 워크플로우는 사용자/프로젝트가 제공한 로컬 PRD 파일(Phase 2, “READ PRD: {prd} 파일을 읽는다”)의 체크리스트 항목을 읽고 처리하므로, 외부 사용자가 주입한 자유 텍스트가 PRD를 통해 LLM에 직접 유입될 수 있습니다.

Issues (2)

W007
HIGH

Insecure credential handling detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
HIGH
Analyzed
Aug 25, 2026, 01:41 PM
Issues
2
Security Audit — snyk — autodev