AgentChat-IndependentTasks
Warn
Audited by Snyk on Oct 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow consumes untrusted web pages and Moodle content via
moodle_scraper.jsin Step 0, which ingests outsider-authored text and feeds it into the task processing pipeline.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata