assurance-review
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it processes content from external sources.
- Ingestion points: The skill explicitly scans '设计、代码和 Agent 指令' (design, code, and agent instructions) within the user's project files (SKILL.md).
- Boundary markers: The instructions do not provide the agent with specific delimiters or strict guidance to ignore potentially malicious prompts embedded within the files being reviewed.
- Capability inventory: The skill has the capability to perform code modifications ('若获授权修复，只做所需改动') and can transition tasks to other skills like 'design-forge' or 'defrag'.
- Sanitization: There is no evidence of sanitization, filtering, or escaping logic applied to the external data before it is integrated into the agent's reasoning process.
Audit Metadata