create-system-prompt

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill explicitly asks the user for the full "agent instructions / system prompt" and instructs contributors to copy that system prompt verbatim into the readme, which would force the LLM to output any secrets (API keys, tokens, passwords) contained in the prompt.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow has the user paste their “Agent instructions / system prompt” (outsider-authored free text relative to the skill) and then instructs the agent to copy it verbatim into samples/agent-instructions/{agent-name}/readme.md, which becomes LLM-readable prose in the generated output context.