cn-mlps-checklist
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information regarding system architecture and data sensitivity to generate compliance reports. While this presents a theoretical injection surface, the skill lacks any capabilities (such as tool usage, file system access, or network operations) that could be exploited via malicious input.
- Ingestion points: User inputs regarding system functionality, architecture, and impact assessments (defined in SKILL.md under 'Required Inputs').
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: None. The skill does not use any tools or scripts.
- Sanitization: Not applicable as the skill only generates structured text output.
Audit Metadata