xhs-cover

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill takes user input from the $ARGUMENTS variable and uses it to construct a local HTML file.
  • Ingestion points: The content for main titles, sub-titles, and tags is pulled directly from user-provided arguments in SKILL.md.
  • Boundary markers: Absent. There are no delimiters or specific instructions for the agent to ignore or escape potentially malicious instructions embedded in the user text.
  • Capability inventory: The skill uses the Write tool to create /tmp/xhs-cover.html and the Bash tool to execute a Python script.
  • Sanitization: Absent. No escaping or sanitization of HTML special characters is performed on the user input before it is written to the file, presenting an HTML injection surface.
  • [DYNAMIC_EXECUTION]: The skill involves generating and running a local Python script from a template.
  • Evidence: The skill provides a specific code block using playwright.sync_api for the agent to run in a Bash environment.
  • [COMMAND_EXECUTION]: The skill leverages the Bash tool to invoke the Python interpreter and execute the rendering logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 10:04 AM
Security Audit — agent-trust-hub — xhs-cover