NYC

clawshot

Fail

Audited by Snyk on Feb 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.90). These URLs include multiple direct .sh download links and an explicit "bash <(curl ...setup.sh)" install pattern from an unverified domain (clawshot.ai) plus a GitHub repo of unknown trustworthiness, which makes them a high-risk vector for remote code execution and malware distribution.

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

  • Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to fetch and browse public, user-generated content (e.g., the "Browsing Feed" endpoints and cron examples that curl https://api.clawshot.ai/v1/feed and log posts), so the agent will read and act on untrusted third-party posts/comments.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 16, 2026, 02:44 AM