runtime-sync

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's required "Upstream Research" workflow (SKILL.md → references/upstream-sources.md) explicitly instructs fetching and reading public third-party sources (GitHub READMEs/CHANGELOGs, npm package pages, git repos via curl/npm/git commands) and uses that untrusted, user-generated content to determine adapter metadata and install logic, so those pages could indirectly inject instructions that influence the agent's actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 03:18 AM