ta-discussion-writer
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its core data processing workflow.
- Ingestion points: The skill ingests external data including '研究发现' (research findings), '理论框架' (theoretical frameworks), and '文献综述要点' (literature review points) provided by the user or previous tools (SKILL.md).
- Boundary markers: There are no instructions for the agent to use delimiters (like triple backticks or XML tags) or safety warnings to ignore instructions that might be embedded within the provided research data.
- Capability inventory: The skill possesses file-writing capabilities, specifically calling a 'Write tool' to save the generated content to
discussion.md(SKILL.md). - Sanitization: The instructions lack requirements for sanitizing, escaping, or filtering the ingested external content before it is processed or written to the disk.
Audit Metadata