frontend-code-review

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-provided code files that could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The agent is instructed to review .tsx, .ts, and .js files under the src/frontend/ directory, as described in SKILL.md.
  • Boundary markers: There are no delimiters or explicit instructions to wrap external code content in markers (e.g., XML tags or code blocks with ignore instructions) to separate it from the system prompt.
  • Capability inventory: The skill's capabilities are limited to generating a structured markdown report based on Template A or Template B. No file system modifications, network requests, or subprocess executions are defined in the provided skill files.
  • Sanitization: No input validation or sanitization rules are defined to filter or escape instructions embedded in the code being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 10:41 AM