deep-trace

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read files/diffs and output actual code lines verbatim (including the extension table and copying it to the clipboard), which would expose any hard-coded API keys, tokens, cookies, or passwords found in the code—creating a direct secret-exfiltration risk.