chat-profile-analysis

Fail

Audited by Snyk on Feb 27, 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 explicitly instructs loading and quoting original chat messages as evidence (including reading local JSONL/SQLite chat histories and appending dialogue excerpts), which forces the LLM to reproduce verbatim user/AI content that may contain API keys, tokens, or passwords — creating a high exfiltration risk.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 27, 2026, 03:26 PM