anti-deception

Warn

Audited by Snyk on Jul 2, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill’s required runtime workflow calls an anti-deception tool from the ejentum MCP server and uses the tool’s returned scaffold text as LLM context; since the MCP server/tool output is not shown as operating-user-authored or tenant-owned, it is an outsider-authored free-text source that the LLM ingests.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 2, 2026, 01:16 PM
Issues
1
Security Audit — snyk — anti-deception