writing-assistant
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied thoughts and ideas to generate structured markdown documents, creating a surface where untrusted input influences agent-generated files.
- Ingestion points: User input defining themes and ideas in stages 01, 02, and 03.
- Boundary markers: The skill lacks explicit instructions for the agent to use secure delimiters or ignore instructions within user-provided content.
- Capability inventory: The agent has the capability to write local markdown files using dynamic filenames based on user input (e.g.,
{主题}_insights.md). - Sanitization: No explicit sanitization or input validation for filenames or content is specified.
Audit Metadata