product-hunt-launch
Warn
Audited by Snyk on Mar 7, 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.md explicitly runs public web search apps (e.g., "infsh app run tavily/search-assistant" and "infsh app run exa/search" in the Quick Start and Research sections) to ingest Product Hunt launches and community sentiment from the open web, which the agent is expected to read and use to drive launch decisions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly invokes the inference.sh CLI (https://inference.sh) at runtime to run remote apps (e.g., falai/flux-dev-lora, tavily/search-assistant) which execute remote model/app code and directly affect prompts/results, and those external apps are relied on as required runtime dependencies.
Audit Metadata