mtm-doc-migrate
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and merges content from external source documents that could contain malicious instructions designed to influence agent behavior.
- Ingestion points: The agent is instructed to "完整阅读被合并的文档" (read source documents completely) as defined in SKILL.md.
- Boundary markers: There are no specific instructions or delimiters mentioned to isolate source document content or to treat it strictly as data, increasing the risk that embedded instructions could be executed.
- Capability inventory: The skill gives the agent the ability to read multiple source files, merge content into a target document, and delete source files or chapters ("删除源文档对应的章节"), which could be abused if malicious instructions are present in the documents.
- Sanitization: The skill lacks any instructions for sanitizing or validating the content of the source documents before processing or merging them.
Audit Metadata