parallel
Warn
Audited by Snyk on Mar 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill explicitly performs web search and page extraction of arbitrary public URLs via Parallel.ai (see SKILL.md/README) and the runtime scripts (scripts/search.py, scripts/extract.py, scripts/task.py, scripts/monitor.py) ingest and display excerpts/full content from third‑party sites which the agent reads and uses to drive research, reports, and task outputs—exposing it to untrusted user-generated web content that could contain indirect prompt injections.
Audit Metadata