ui-code-review

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from pull request diffs and source code, creating a potential for indirect prompt injection. \n
  • Ingestion points: Pull request diffs, component source code, and screenshots referenced in the review process (SKILL.md). \n
  • Boundary markers: The instructions do not define delimiters or specific 'ignore' directives to prevent the agent from executing instructions potentially embedded within the code diffs. \n
  • Capability inventory: The skill consists only of markdown instructions and configuration; it contains no script files, subprocess executions, or network access tools. \n
  • Sanitization: There are no documented procedures for sanitizing or validating the content of the pull requests before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:31 PM
Security Audit — agent-trust-hub — ui-code-review