create-backlog-item

Fail

Audited by Snyk on Mar 29, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill mandates always including a "verbatim user report" field (and may include user-provided "how to reproduce" steps) verbatim in the MCP call and output, which forces the LLM to emit any secrets the user pasted (API keys, tokens, passwords) exactly as given, creating an exfiltration risk.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Mar 29, 2026, 08:41 AM
Issues
1