The Agent Skills Directory

[DATA_EXFILTRATION]: The skill performs network requests to doubaoya.com to gather account metrics. This is the intended purpose of the diagnostic tool and is implemented transparently.
[COMMAND_EXECUTION]: The skill executes a local Python script (analyze_xhs_account.py) to facilitate API communication. The script uses standard libraries and follows best practices for secret management by reading the API key from environment variables.
[PROMPT_INJECTION]: The skill processes data from an external API, which constitutes an indirect prompt injection surface. 1. Ingestion points: The agent processes JSON data returned by the diagnostic script which contains external account metrics and profiles. 2. Boundary markers: The instructions specify a narrative structure but do not include explicit delimiters or 'ignore embedded instructions' warnings to separate external data from instructions. 3. Capability inventory: The skill is limited to executing the provided Python script for data retrieval; it does not possess file-writing or broader network capabilities. 4. Sanitization: No specific filtering or escaping of the API response is implemented before it is processed by the agent.

xiaohongshu-account-analyzer