embedded-dev-antigravity

Fail

Audited by Snyk on Feb 27, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to ask the user for Wi‑Fi SSID and password and then embed the password verbatim into commands (e.g., nmcli ... password ) that the agent will generate/execute via fastmcp, creating direct secret exposure and exfiltration risk.

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

  • Third-party content exposure detected (high risk: 0.90). SKILL.md Step 3 explicitly requires performing web_search against public sites (e.g., docs.espressif.com, docs.zephyrproject.org, site:github.com) and mandates using those search results in technical answers and to generate commands/calls (see Steps 5 and 7), so the agent will read and act on untrusted third-party content that could influence tool use.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 27, 2026, 02:46 AM