content-inventory

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to extract and "preserve exact current text verbatim" from every text layer and include those strings in its output inventory, so any secrets present in the design (API keys, tokens, passwords) would be reproduced verbatim and exposed by the LLM.