termination-review
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data in the form of termination case descriptions and attached legal documents.
- Ingestion points: User inputs provided via the
argument-hintand the 'Basic Facts' (基本事实) step in the workflow. - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded prompts within user-provided data.
- Capability inventory: The skill possesses capabilities to read local configuration files from
~/.claude/plugins/config/, read and write case files (matter.md), and invoke external legal research connectors. - Sanitization: The skill does not specify any sanitization, filtering, or validation of user-provided content before processing it in the legal review workflow.
Audit Metadata