update

Warn

Audited by Snyk on Jul 21, 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 describes a runtime workflow where /playbooks:update --apply fetches upstream content and replaces each pack’s vendor/SKILL.md (untrusted third‑party DATA); since vendor/SKILL.md can contain free-text instructions, this constitutes outsider-authored text entering the agent context via the upstream-fetched file (even if the playbook says not to follow it).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 21, 2026, 07:55 PM
Issues
1
Security Audit — snyk — update