xiaohongshu-comment
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (
fetch_xhs_comments.py) to handle API interactions. This is a standard and safe implementation for this type of functionality. - [EXTERNAL_DOWNLOADS]: The skill performs POST requests to
https://doubaoya.comto retrieve comment data. This external communication is the documented and intended purpose of the skill. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-generated comments from an external platform (Xiaohongshu).
- Ingestion points: Data is fetched from an external source (Xiaohongshu comments) via an API and then analyzed by the agent.
- Boundary markers: None. There are no explicit instructions or delimiters provided to separate the untrusted comment text from the agent's analysis instructions.
- Capability inventory: The agent has the capability to execute local scripts and perform complex text analysis on fetched data.
- Sanitization: No sanitization or escaping of the comment content is performed before analysis, which could allow instructions embedded in comments to influence the agent.
Audit Metadata