takt-task-builder

Warn

Audited by Snyk on Mar 10, 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 explicitly ingests third‑party, user‑generated content — e.g., it supports creating tasks from GitHub Issues/PR comments ("GitHub Issueからタスク作成", "takt add #N" / "takt add --pr") and can pull external repertoire packages from GitHub (repertoire add), and documentation also references WebSearch/WebFetch; those external inputs are read and injected into prompts/workflow and can change subsequent tool actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 01:10 AM