find-agents

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly directs fetching/installing agents from public repositories and arbitrary URLs (e.g., "npx agentshq add /" and "npx agentshq add "), so the agent will ingest untrusted, user-generated third‑party content that can influence install decisions and subsequent behavior.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly supports installing agents from external repositories/URLs at runtime (e.g., "npx agentshq add " or "npx agentshq add /" / git@github.com:org/repo.git), and those fetched repo/URL contents are translated into agent definitions that directly control prompts/instructions, so this is a runtime dependency that can control agent behavior.