mouse-swarm-reveal

Fail

Audited by Snyk on Nov 13, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill's visual reveal and status-view code is legitimate and self-described, but the npx --yes line runs unpinned GitHub package code without vetting, which is risky toward the user even though it is documented and not clearly malicious.

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

  • Third-party content exposure detected (low risk: 0.10). The required Ruflo observation path polls agent registrations and statuses from the local Ruflo CLI (SKILL.md:56), which is the user's own system state; an outsider has no direct submission path into it, but agent labels and roles are free text that could be shaped indirectly, so this is rated low under recall-first.

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

  • Potentially malicious external URL detected (medium risk: 0.30). The skill's setup instructs npm install github:ruvnet/mouse-swarm and npx --package=github:ruvnet/mouse-swarm, which fetch and execute unpinned code from an individual-owned GitHub repository, so it is an unofficial dependency with no concrete warning sign and no strong first-party provenance, giving a medium tier.

Issues (3)

E004
CRITICAL

Prompt injection 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
Nov 13, 2026, 04:07 PM
Issues
3