agency-legal-client-intake
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security vulnerabilities, malicious code, or suspicious patterns were detected. The skill is entirely composed of text-based instructions and templates for legal intake specialists.
- [PROMPT_INJECTION]: The skill processes untrusted input from prospective clients (e.g., case descriptions and legal facts), which is a inherent surface for indirect prompt injection. However, the skill lacks high-risk capabilities such as network access, file system writes, or shell execution that could be leveraged by an attacker.
- Ingestion points: Case descriptions and fact-gathering sections in the
SKILL.mdquestionnaires. - Boundary markers: No explicit delimiters are used in the provided text templates to separate user input from instructions.
- Capability inventory: The skill is limited to text generation and summarization for attorneys; it has no access to sensitive system tools or network endpoints.
- Sanitization: The instructions do not define specific sanitization or validation logic for data collected from prospects.
Audit Metadata