zg-socratic-problem-locator
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, including chat history, file attachments, and images provided by the user.
- Ingestion points:
SKILL.mdexplicitly instructs the agent to utilize "全部对话历史、附件、图片、文件和数据" (all dialogue history, attachments, images, files, and data) as the primary evidence source for problem diagnosis. - Boundary markers: The instructions do not mandate the use of delimiters or specific markers to separate processed data from the agent's core instructions.
- Capability inventory: The skill does not request or use any tools for persistent file modification, network exfiltration, or system command execution.
- Sanitization: There are no instructions provided to sanitize input or to ignore potentially malicious instructions embedded within the analyzed materials.
Audit Metadata