autoplan

Fail

Audited by Snyk on Nov 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is an auto-review pipeline whose guard hooks, path checks, and gate flow all serve its advertised review purpose; the only sketchy item is shadow-decider.md, which records covert predictions of the owner's gate decisions that are never shown to him, hiding the skill's own activity from the user.

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

  • Third-party content exposure detected (low risk: 0.10). The visible required workflow ingests only the user's own plan, repo files, git log/diff, and first-party section files, but the truncated CEO/design/eng section bodies may require WebSearch, which would make arbitrary web results an outsider-text path (low).

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 16, 2026, 08:17 PM
Issues
2