code-explainer

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied code snippets which may contain instructions designed to manipulate the agent's output.
  • Ingestion points: User input enters the agent context through code snippets provided for explanation.
  • Boundary markers: The instructions in SKILL.md lack delimiters (such as XML tags or triple quotes) or explicit directives for the agent to ignore any instructions embedded within the analyzed code.
  • Capability inventory: The skill uses the run_js tool to execute a script (scripts/index.html) that generates a webview UI (assets/webview.html) to display the results.
  • Sanitization: The webview correctly uses .textContent for DOM updates, which prevents Cross-Site Scripting (XSS); however, there is no validation or filtering to prevent the agent from following malicious commands hidden within the user data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 08:22 AM
Security Audit — agent-trust-hub — code-explainer