bump-deps

Warn

Audited by Snyk on Mar 1, 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 runs the taze CLI via scripts/run-taze.sh and explicitly instructs (SKILL.md Steps 1–2) to parse taze's output to decide which packages to update—this output is derived from public package registries (e.g., npm) and thus untrusted third-party package metadata can directly influence the agent's update decisions and tool usage.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 01:32 AM