xhs-publisher

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill handles untrusted user data which could influence agent behavior through indirect prompt injection.
  • Ingestion points: User-provided inputs for title, content, and tags are used throughout SKILL.md to populate web forms.
  • Boundary markers: The instructions lack delimiters or clear instructions for the agent to ignore potential directives embedded within the user content.
  • Capability inventory: The skill uses browser automation actions such as click, type, and form_input in SKILL.md to interact with the web interface.
  • Sanitization: No validation or sanitization of the user input is specified before it is injected into the target platform's DOM elements.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 03:42 AM