opensource-housekeeper

Fail

Audited by Snyk on Jul 29, 2026

Risk Level: CRITICAL
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.90). The skill includes a pattern that embeds a user PAT directly into commands/URLs (URL_WITH_TOKEN=$(...https://{PAT}@...)), which would require the LLM to handle or emit the token verbatim, creating an exfiltration risk despite other notes advising not to post PATs in chat.

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.80). Multiple entries are third‑party GitHub mirrors/proxies (ghfast.top, ghproxy.net, gh-proxy.com, mirror.ghproxy.com, kgithub.com) and an in-URL PAT placeholder — these proxies/typosquat domains can modify or obscure upstream content and embedding credentials in URLs is dangerous, so they are suspicious sources for distributing code or executables.

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

  • Third-party content exposure detected (low risk: 0.10). 主线 B 在 Step A3/A5 会对用户输入的项目名/新闻进行多平台搜索(curl)并据此拉取/读取仓库内容(例如 README/Quick Start),因此外部文字会被经由“搜索结果/页面片段/仓库文件”进入运行时上下文。

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The skill explicitly runs git clone / curl against user-supplied or example repository URLs (e.g., https://github.com/facebook/react and mirror https://ghfast.top/https://github.com/owner/repo) and then installs/starts the cloned project's dependencies (pip/npm/cargo), so remote repository content fetched at runtime can result in execution of arbitrary code.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs running privileged commands (e.g. sudo pfctl -d, sudo sntp -sS) and suggests security-bypassing workarounds (e.g. GIT_SSL_NO_VERIFY=1), which request elevated privileges or disabling protections on the host.

Issues (5)

W007
HIGH

Insecure credential handling detected in skill instructions.

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Jul 29, 2026, 01:36 AM
Issues
5