daily-log
Fail
Audited by Snyk on Feb 26, 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 asks the agent to extract and compile session contents including the user's initial prompt and key actions from JSONL files into a markdown log without any redaction instructions, so any secrets present in those prompts/outputs would be reproduced verbatim (exfiltration risk).
Audit Metadata