moli

Fail

Audited by Snyk on Aug 14, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.90). Direct download links to installer scripts (.sh and .ps1) on the project's GitHub releases — and the skill's recommended curl/irm | sh/iex installation pattern — are high-risk for distributing unvetted executables.

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

  • Third-party content exposure detected (medium risk: 0.30). In the required runtime workflow, the agent ingests outsider-authored free text when it executes moli fetch ... "<url>" and then serializes the fetched page’s rendered DOM/content (e.g., --dump markdown/json/html/semantic_tree_text), which can contain attacker-provided instructions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

Issues (3)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
CRITICAL
Analyzed
Aug 14, 2026, 06:44 AM
Issues
3
Security Audit — snyk — moli