ui-review
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local
gitcommands (git status,git diff) and a repository-specific analysis script (.claude/scripts/code_graph) to determine review scope and analyze component dependencies.\n- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection (Category 8) as it processes data from external frontend files.\n - Ingestion points: Frontend source code files and git diff outputs are read into the agent's context during the review phases.\n
- Boundary markers: The instructions do not define boundary markers (such as XML tags or specific delimiters) to separate untrusted code content from the agent's instructions.\n
- Capability inventory: The skill possesses significant capabilities, including spawning sub-agents (
spawn_agent), executing local shell scripts, and writing reports to the filesystem.\n - Sanitization: No sanitization or validation of the ingested code content is performed before interpolation into the prompt context.
Audit Metadata