blur-sensitive-info

Fail

Audited by Snyk on Jul 10, 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 find and report sensitive items (explicitly naming "tokens/API keys/passwords") and to "tell the user what was blurred," which can lead the LLM to transcribe or output secret values verbatim.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Jul 10, 2026, 09:42 AM
Issues
1
Security Audit — snyk — blur-sensitive-info