parallel-data-enrichment

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly says this tool "Adds web-sourced fields (CEO names, funding, contact info)" and instructs the agent to run parallel-cli enrichment, poll and read the resulting JSON output (preview rows and use them), so the agent consumes untrusted public web–sourced content that can influence subsequent decisions/actions.