skill-advisor

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

• Third-party content exposure detected (high risk: 1.00). The skill's Gap Installation Flow (SKILL.md and README.md) explicitly instructs the agent to run npx skills find <keyword> and npx skills add <owner/repo@skill> to search for and install public community skills (GitHub/npm), which fetches and ingests untrusted third‑party repositories/metadata that can change the agent's tools 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’s gap-install flow runs npx to fetch and install external packages at runtime (e.g., "npx skills add j4rk0r/claude-skills --skill skill-advisor --yes --global" and the generic "npx skills add owner/repo@skill -y --agent claude-code"), which will fetch and execute remote code and is required for installing gaps, so it is a runtime external dependency that can execute code.