weibo-trends-analyzer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt embeds a concrete API key in the default API URL and shows curl commands and metadata that require the agent to include that key verbatim in requests/output, which is direct secret handling/exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches real-time Weibo hot search data from a public TianAPI endpoint (https://apis.tianapi.com/weibohot/...) and explicitly performs web searches of social media/news (Weibo, forums, user-generated content) which the agent ingests and analyzes, exposing it to untrusted third‑party content that could carry indirect prompt injection.

HIGH W008: Secret detected in skill content (API keys, tokens, passwords).

• Secret detected (high risk: 1.00). The document contains one hardcoded, high-entropy API key: "4dfdf794141101d7bb8ece0294dbbc02" embedded in the TianAPI endpoint (https://apis.tianapi.com/weibohot/index?key=4dfdf794141101d7bb8ece0294dbbc02) and shown in the curl example. At 32 hex characters (~128 bits) it is a random-looking, usable credential and should be treated as a secret.

No other real credentials were found. Other strings in the doc are placeholders or low-entropy examples (e.g., "YOUR_API_KEY", "sk-xxxx", simple example passwords) and were intentionally ignored per the rules.