canvas-discussion-facilitator
Warn
Audited by Snyk on Sep 15, 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 agent reads student-authored discussion posts from Canvas LMS via MCP tools (
list_discussion_entries,get_discussion_entry_details), allowing any student or outsider posting in the course forum to inject untrusted free text into the agent's context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata