NYC

astro-expert

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: 0.80). The mandatory Memory Protocol instructs the agent to run "cat .claude/context/memory/learnings.md" before starting, which forces it to output the contents of a local file (potentially containing API keys/secrets) verbatim and thus creates an exfiltration risk, even though other parts recommend environment-variable handling.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 02:47 AM