search-paper

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs running search-paper-cli (SKILL.md and references/USAGE.md) to search public providers like arxiv/semantic/crossref and to retrieve/extract paper text via "get --as text" (and the install script downloads release artifacts from GitHub), which causes the agent to ingest untrusted third-party web content that could contain actionable instructions.

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

• Potentially malicious external URL detected (high risk: 0.90). The ensure script fetches and installs executable code at runtime from GitHub (via go install github.com/jtsang4/search-paper-cli/cmd/search-paper-cli and by downloading release artifacts from https://github.com/jtsang4/search-paper-cli/releases/latest/download/), which executes remote code the skill depends on.