compress-prompt

Fail

Audited by Snyk on Mar 10, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). Because the skill mandates reproducing the input prompt's content (especially in lossless mode) with no redaction or secret-handling rules, any API keys/passwords/cookies present in P would be included verbatim in the output, enabling exfiltration.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 10, 2026, 01:57 AM