devex-review

Fail

Audited by Snyk on Nov 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate DX audit whose browser, CLI, and telemetry steps are documented, but its open-ended Aside exec path sends a page-reading prompt to a third-party agent that operates on the user's signed-in sessions, which is a data flow the user may not expect.

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

  • Third-party content exposure detected (medium risk: 0.30). Step 7 requires gh reads of GitHub issues (response time, templates, labels), and any GitHub issue reading is medium because outsiders can file issues the workflow ingests without the agent selecting a specific one; the docs pages read in Steps 1 and 4 are user-named targets, which add low-risk exposure.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 16, 2026, 08:17 PM
Issues
2