literature-review

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses parallel-cli search (and often parallel-cli extract) to fetch and ingest web page/paper text from public scholarly domains (e.g., Google Scholar/arXiv/PubMed/Nature) into the agent’s context, which is outsider-authored free text from third parties.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's Required CLI Tools section instructs running a remote installer via curl -fsSL https://parallel.ai/install.sh | bash which fetches and immediately executes remote code (install script) and is required because the skill depends on the parallel-cli for runtime searches.