vestige-auto-memorise

Fail

Audited by Snyk on Jun 16, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to take arbitrary conversation text and interpolate it verbatim into CLI invocations (e.g., vestige decision add ""), so if that text contains API keys, tokens, or passwords the LLM will output them directly — creating a clear exfiltration risk.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Jun 16, 2026, 08:27 PM
Issues
1
Security Audit — snyk — vestige-auto-memorise