html-communication

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes platform-specific commands (open, xdg-open, or start) to launch generated HTML artifacts in a web browser for human review. These commands are limited to opening the resulting file and are fundamental to the skill's primary purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information to create HTML content, creating a surface for indirect prompt injection if the input contains malicious scripts. This is mitigated by instructions prohibiting network dependencies in the output and requiring human approval for external publishing.
  • Ingestion points: Data from plans, specs, findings, or reports provided by the user (SKILL.md).
  • Capability inventory: File writing to the local temporary directory and execution of system commands to open files in a browser (SKILL.md).
  • Boundary markers: None explicitly defined for user-provided data.
  • Sanitization: No specific escaping or sanitization requirements are mentioned for the content rendered into HTML.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 12:27 AM
Security Audit — agent-trust-hub — html-communication