review-structure

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). Because the prompt's anti-confabulation gate forces the agent to echo exact file:line code excerpts read in the current turn, any secrets present in those files (API keys, tokens, passwords) would be required to be reproduced verbatim in the output, creating an exfiltration risk.