thesis-visual-layout-planner
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface by ingesting external user-supplied data (thesis chapters and outlines).
- Ingestion points: The workflow involves reading '各章 Markdown' (Markdown chapters) and '稳定版大纲' (stable outlines) as specified in
SKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions potentially embedded within the thesis content.
- Capability inventory: The skill allows writing generated figure plans and mermaid diagrams to the local file system within the
codex_md/andtmp_layout/directories. - Sanitization: No explicit sanitization or validation logic is defined for the content processed from the input Markdown files.
Audit Metadata