developer-growth-analysis

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill requires reading raw chat history and pasted contents (which may contain API keys, tokens, or passwords) and instructs the agent to include evidence from that history in generated reports and send them to Slack, which can cause secrets to be reproduced verbatim in outputs—an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly uses Rube MCP to search and ingest HackerNews posts (see "Search for Learning Resources" / step 5 in SKILL.md) — a public, user-generated site — and the agent is expected to read and interpret those results to select and summarize curated resources as part of its runtime workflow, so untrusted third-party content can influence its decisions and outputs.