scraping-recon
Fail
Audited by Snyk on Mar 9, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). This skill explicitly instructs extracting authentication headers, cookies, and "the full request" and to replay them (e.g., curl -H "Cookie: session=abc123"), which requires handling and embedding secret/session values verbatim in outputs/commands, creating an exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly directs the agent to fetch and analyze public third‑party content (robots.txt, sitemaps, page source, rendered DOM, network XHR/API/GraphQL responses) and to use those findings to choose scraping tools and next actions, so untrusted web content can materially influence behavior.
Audit Metadata