work-with

Warn

Audited by Snyk on Jun 18, 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). Outsider free text can enter the LLM context via --sync/--checkpoint when the skill reads partner-provided SYNC-RESULT/checkpoint text from maw hey or /wormhole and then uses it to update local topic/state (the protocol payload includes free-form EVIDENCE/amendment text).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 18, 2026, 01:15 PM
Issues
1
Security Audit — snyk — work-with