python-executor
Warn
Audited by Snyk on Feb 18, 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 exposes web-scraping and HTTP libraries (requests, BeautifulSoup, Selenium, Scrapy) and includes examples that call arbitrary public URLs (e.g., the "Web Scraping" example using requests.get("https://example.com") and the "API Calls" example using api.github.com), so the agent can fetch and parse untrusted, user-generated web content at runtime.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill invokes the inference.sh platform at runtime (via the infsh CLI / service) to execute arbitrary Python code remotely (e.g., https://inference.sh / https://cli.inference.sh), so the external service is used during runtime to run code.
Audit Metadata