review-frontend
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands like
git diff,grep, and project-specificnpmscripts (lint,typecheck,test). Executing scripts defined in an untrusted repository'spackage.jsonposes a security risk as these scripts can be modified to run arbitrary code. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests untrusted code and diffs and uses them to guide agent behavior.
- Ingestion points: Target files and
git diffoutput (referenced inSKILL.md). - Boundary markers: Absent; instructions do not provide delimiters or warnings to ignore embedded instructions in the code being reviewed.
- Capability inventory: Shell access (
git,grep,npm) and tool-based skill/task management (referenced inSKILL.md). - Sanitization: Absent; content from the repository is processed without validation or escaping.
Audit Metadata