films-search
Fail
Audited by Snyk on Mar 2, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill explicitly extracts and returns share "extractCode" values (passwords) and direct pan URLs in its JSON and agent output, requiring the LLM/agent to include secret-like values verbatim in responses.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly performs web-search discovery and JavaScript deep page scraping (see SKILL.md and scripts/film-search.js calling the web-search bridge and scripts/shared/deep-extract.js which fetches arbitrary web pages and Baidu results) to ingest public/third‑party pages and extract links/extract-codes that directly drive search results and subsequent actions, so untrusted user-generated web content can influence the agent's behavior.
Audit Metadata