sequencer

Fail

Audited by Snyk on Mar 5, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The sequencer instructs the LLM to embed arbitrary step "args" and prior-step outputs verbatim into subagent prompts, plan displays, and run files, so any API keys/passwords present in a pipeline would be included in generated output (prompts/files), creating a direct exfiltration risk.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 5, 2026, 11:50 PM