skills/mizchi/skills/frontend-expert/Gen Agent Trust Hub

frontend-expert

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill's operations are confined to the local repository and follow the intended purpose of performing a code review.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use git log to identify files modified in the last week. This is a functional requirement for the code review process and does not involve risky arguments or user input injection.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project source code and JSON audit reports which could contain malicious instructions.
  • Ingestion points: Reads files from src/ and .frontend-review/report/latest/raw/.
  • Boundary markers: Absent. The skill does not define specific delimiters to separate untrusted code from instructions.
  • Capability inventory: The skill has no network access and primarily performs read/write operations for report generation.
  • Sanitization: No input sanitization is specified, but the limited capabilities of the skill minimize the risk of exploitation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 03:37 AM
Security Audit — agent-trust-hub — frontend-expert