web-fetch
Fail
Audited by Snyk on Feb 16, 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 accepts arbitrary headers and its examples show embedding an Authorization token directly in a command-line header, which invites the agent to include secret values verbatim in generated commands/requests and therefore creates exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill issues HTTP requests to arbitrary URLs (see "python ~/.copilot/skills/web-fetch/web_fetch.py " and the description "HTTP requests to URLs"), so it can fetch untrusted, user-provided web content that the agent will read and return, enabling indirect prompt injection.
Audit Metadata