web-fetch
Fail
Audited by Snyk on Feb 15, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt includes curl examples that embed an Authorization header with a Bearer TOKEN, which instructs placing secrets directly into commands/requests and can cause the model to output secret values verbatim.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and reads arbitrary public web pages and APIs (via WebFetch, curl, lynx, w3m) from user-provided URLs, causing the agent to ingest untrusted third-party content from the open web that could contain indirect prompt injection.
Audit Metadata