literature-review

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

• Third-party content exposure detected (low risk: 0.10). The literature review workflow uses parallel-cli search and database access skills to fetch and screen academic papers and preprints written by external researchers, which the agent ingests as free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation of parallel-cli via an external shell script from https://parallel.ai/install.sh, which is an unverifiable third-party setup dependency lacking official publisher provenance.