html-code-review

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from pull requests, diffs, and codebase subsystems.
  • Ingestion points: PR diffs, refactor descriptions, and source code files are processed to generate the HTML artifacts.
  • Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore instructions embedded within the reviewed code.
  • Capability inventory: The skill has the capability to write files (<topic>-<kind>.html) and generate JavaScript logic within those files, including mention of clipboard and network access for submit handlers.
  • Sanitization: The skill explicitly mandates safe DOM construction (using textContent and createElement) and forbids the use of innerHTML with variable data to prevent XSS vulnerabilities in the generated output.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 12:57 PM
Security Audit — agent-trust-hub — html-code-review