AGENT LAB: SKILLS

http-api-cloudbase

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). This skill instructs embedding Authorization: Bearer directly into example curl commands and tells users to replace placeholders with real keys, which encourages the LLM to include secret values verbatim in generated requests/commands.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 08:13 PM