wilma

Warn

Audited by Snyk on Mar 6, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to use the wilma CLI to fetch and read user-generated Wilma content (e.g., "wilma summary", "wilma news read", "wilma messages read") and to interpret/prioritize actionable items from those messages/news, which are third-party, untrusted user-generated inputs that can influence agent decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 08:48 AM