provider-switch

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks the user to enter API keys and shows a command that injects the key via stdin (printf 'KEY_VALUE' | ...), meaning the agent will receive and must place the secret into executed commands/outputs, creating a high risk of verbatim secret exposure.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). SKILL.md → P1 (required) runs bash "${CLAUDE_SKILL_DIR}/scripts/detect-mode.sh" "$ARGUMENTS" where position 1 of $ARGUMENTS is explicitly defined as a free-form prompt from the user, and then the workflow proceeds based on that untrusted text.