cli-hub-meta-skill

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). The links point to a GitHub repo and GitHub Pages (no direct executables or URL shorteners), but the skill instructs pip-installing code directly from an unknown GitHub account/repository—which can execute arbitrary code—so while hosting is reputable the source itself is untrusted and potentially risky.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and parse the live catalog at https://hkuds.github.io/CLI-Anything/SKILL.txt (a public GitHub Pages URL) and then use its supplied pip install commands and usage patterns to select and run CLIs, which means untrusted third‑party content can directly influence tool installation and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to fetch the live catalog at https://hkuds.github.io/CLI-Anything/SKILL.txt at runtime, which contains pip install/git+https://github.com/HKUDS/CLI-Anything... commands that would cause the agent to download and execute remote code (so the fetched content directly controls runtime actions).