improve-skill
Fail
Audited by Snyk on Feb 15, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt explicitly asks the user to paste raw session transcripts into the analysis prompt and to generate/write improved skills based on that content, which can cause the LLM to ingest and reproduce any API keys, tokens, or passwords present in those transcripts, creating a high exfiltration risk.
Audit Metadata