experience-lwc-rtl-validate

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local utility scripts/scan-rtl-css.sh using python3. This script contains a deterministic regex-based scanner that identifies physical CSS properties (like margin-left or text-align: left) and suggests their logical equivalents for RTL compliance.
  • [DATA_EXPOSURE]: The skill reads LWC source files (.html, .js, .css) to perform its analysis. This file access is local and limited to the component directory specified by the user, which is necessary for the skill's primary function.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes untrusted source code which could contain malicious instructions in comments or string literals.
  • Ingestion points: Component source files (.html, .js, .css, .ts) located in the project's modules directory (File: SKILL.md).
  • Boundary markers: Absent; the instructions do not define specific delimiters or warn the agent to ignore natural language instructions that might be embedded within the code content.
  • Capability inventory: The skill allows reading local files, executing a local Python script, and writing modifications back to the component files (File: SKILL.md, Step 6 & 7).
  • Sanitization: Absent; the agent is expected to interpret the code content directly to find RTL violations without an intermediate sanitization layer.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 04:58 PM
Security Audit — agent-trust-hub — experience-lwc-rtl-validate