cold-call-prep
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill accesses a specific configuration file located at
~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md. This access is used to load class schedules and professor profiles to tailor the drilling experience. This is a functional requirement for the 'Claude for Legal' plugin ecosystem and does not target sensitive system credentials or personal data. - [PROMPT_INJECTION]: The skill includes instructions for a 'Real-matter check' that triggers a refusal to provide legal advice if user input appears to involve real-world legal situations. This is an intentional safety guardrail designed to maintain ethical boundaries.
- [PROMPT_INJECTION]: The skill ingests user-provided case texts and citations to generate questions. Although the instructions do not use explicit delimiters to separate this external data from the system prompt, the skill lacks any capabilities (such as network operations or shell execution) that would make it vulnerable to indirect prompt injection attacks.
- [NO_CODE]: The skill contains only natural language instructions within its markdown body and does not include any accompanying scripts or executable files, which significantly reduces the potential attack surface.
Audit Metadata