mdtero

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

• Third-party content exposure detected (low risk: 0.10). The required workflow uses the mdtero discover and mdtero parse tools to search for and ingest external academic literature and web content based on user queries or DOIs/URLs, representing low-risk active retrieval of outsider-authored text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to download and execute an installation script from https://mdtero.com/install.sh (curl -Ls https://mdtero.com/install.sh | sh), which constitutes an unverifiable runtime external dependency from an unofficial/service domain carrying high risk.