tophub-trends
Warn
Audited by Snyk on Feb 28, 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 fetches live trending data from the public TopHub URL (https://tophub.today/hot) as shown in SKILL.md and tophub.ts (fetchHotList → analyzeHotList), then injects those fetched, untrusted third-party items into the Claude prompt for analysis and decision-making, so external content can materially influence the agent's actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill fetches live trending data from https://tophub.today/hot at runtime (via fetchHotList) and injects that content directly into the Claude prompt, so externally-hosted content can directly control model input and enable prompt-injection or data-poisoning risks.
Audit Metadata