load-work

Warn

Audited by Snyk on Jul 17, 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). SKILL.md Phase 3/4 requires reading the full CONTEXT-*-llm.md session file from done/ or current dir (outsider-authored if those files were created by other parties), and then parsing and summarizing its free-text sections (Project/Session/Hot Files/Refs) into the agent’s LLM context.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 17, 2026, 12:05 PM
Issues
1
Security Audit — snyk — load-work