co-check

Warn

Audited by Snyk on Jun 23, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.65). At runtime the skill calls attention_inbox and surfaces “pending handoffs… and any recent claims by other sessions” (e.g., other users/sessions’ messages/claims), which are outsider-authored free text ingested into the agent context via the MCP/API response.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 23, 2026, 03:17 AM
Issues
1
Security Audit — snyk — co-check