flow-interview

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to read and rewrite bead contents or files and to emit shell commands that embed the full refined text (e.g., echo "" | bd update ... or --acceptance="..."), which would force any secret values present in the source to be reproduced verbatim in the agent's output/commands, creating an exfiltration risk.