agent-tracing

Fail

Audited by Snyk on Aug 1, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.80). The CLI explicitly provides flags to print raw environment variables, full user memory, and full message payloads (e.g., --env, --memory, --msg, --msg-input), so an agent using this skill may read and output secret values verbatim if those secrets exist inside snapshots.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Aug 1, 2026, 09:40 AM
Issues
1