case-brief

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of Markdown-based instructions and templates for the AI agent; it does not include any scripts, executable binaries, or external library dependencies.
  • [SAFE]: The skill is instructed to load user preferences from a configuration file at ~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md. This is a targeted access to a configuration file specific to the skill's domain and is used to personalize the briefing format and learning style.
  • [PROMPT_INJECTION]: The skill processes user-supplied case text and citations, which represents an ingestion point for untrusted data. The risk of indirect prompt injection is mitigated by the skill's design and limited capabilities.
  • Ingestion points: User-provided case names, citations, or pasted case text processed in the SKILL.md workflow.
  • Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions for the ingested content.
  • Capability inventory: The skill is restricted to text analysis and response generation; it does not use tools for network access, filesystem writes, or command execution.
  • Sanitization: No explicit input validation or sanitization is performed on the user-provided text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:58 PM
Security Audit — agent-trust-hub — case-brief