xiaohongshu-hot-notes
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The script scripts/fetch_hot_notes.py performs POST requests to https://doubaoya.com/api/apis/xiaohongshu/search-note/call to retrieve data. This is a legitimate use of the vendor's domain for the skill's primary function.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface through the ingestion of external note data.
- Ingestion points: Data is fetched via scripts/fetch_hot_notes.py and displayed by the agent.
- Boundary markers: None; results are rendered directly into markdown.
- Capability inventory: The skill has network capabilities via urllib in scripts/fetch_hot_notes.py.
- Sanitization: None; fetched text is processed without filtering.
Audit Metadata