xy-rednote-title
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data, including topics, industry descriptions, and existing text snippets, which represents an attack surface for indirect prompt injection.
- Ingestion points: User-supplied input gathered during Step 1 of the workflow in
SKILL.md(e.g., "讲什么" and "给谁看"). - Boundary markers: The prompt instructions lack explicit boundary markers or "ignore embedded instructions" warnings for the interpolated user data.
- Capability inventory: The skill is constrained to text generation based on pre-defined templates and does not possess capabilities for file-system modification, network operations, or shell execution.
- Sanitization: There is no evidence of sanitization, escaping, or validation of user-provided content before it is processed by the model.
Audit Metadata