jacky-xhs-check
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text from users for analysis, which represents a standard surface for indirect prompt injection.
- Ingestion points: User-provided Xiaohongshu note content as described in the workflow in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or boundary markers for the user-provided data.
- Capability inventory: The skill is limited to text analysis and report generation; it lacks network access, file system write permissions, and subprocess execution capabilities.
- Sanitization: No input sanitization or validation logic is defined for the processed content.
- [SAFE]: The skill relies on a local reference file for its database. All external links within the documentation point to well-known social media platforms, news services, and content-checking tools. No malicious behaviors such as obfuscation, credential harvesting, or remote code execution were identified.
Audit Metadata