developer-growth-analysis

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the model to read local chat history including pastedContents (which may contain API keys, tokens, or passwords) and to produce and send a complete report to Slack with no redaction or secret-handling safeguards, so the model could output secrets verbatim.

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

• Third-party content exposure detected (high risk: 0.90). This skill's required workflow step "Search for Learning Resources" explicitly uses Rube MCP to search HackerNews (public, user-generated content) and instructs the agent to fetch, read, prioritize, and summarize those posts for the report, which could allow untrusted third-party content to influence agent decisions and actions.