code-review-excellence

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its primary function involves processing untrusted data from external sources which could contain malicious instructions.
  • Ingestion points: As specified in SKILL.md, the agent reads repository rules, task descriptions, and code diffs ('读取仓库规则、任务描述和 diff').
  • Boundary markers: The instructions lack explicit delimiters or mandatory warnings for the agent to ignore instructions embedded within the processed code or PR metadata.
  • Capability inventory: The skill explicitly authorizes the agent to execute powerful tools including build, test, lint, and type checkers ('能运行时执行相关 build、test、lint 和类型检查').
  • Sanitization: There are no instructions provided to sanitize or escape external content before it is processed or used to influence the agent's execution of build and test commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 09:42 AM
Security Audit — agent-trust-hub — code-review-excellence