ta-framework-writer
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external research framework documents provided by the user to generate paper sections. While this introduces a surface for indirect prompt injection if the source documents contain malicious instructions, the impact is limited to text generation, and the skill includes quality checks for citations and theoretical consistency. This is a low-risk inherent characteristic of document-processing skills.
- Ingestion points: Processes
framework_[研究主题].mdfiles or pasted text content. - Boundary markers: None explicitly defined in the prompt instructions.
- Capability inventory: The skill uses a file-writing tool to save generated chapters to the local directory.
- Sanitization: No explicit sanitization of input text is performed before interpolation into the writing tasks.
Audit Metadata