flashcards

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill manages local study materials within a specific application directory. It performs no network operations and does not execute external code or shell commands.
  • [DATA_EXFILTRATION]: No data exfiltration detected. File system access is restricted to the skill's own configuration and data paths within the home directory (~/.claude/plugins/config/claude-for-legal/). No sensitive system configuration files or credentials are targeted.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from user-provided outlines and notes, creating an indirect prompt injection surface.
  • Ingestion points: Local files CLAUDE.md, cards.md, and user-provided source paths or text (SKILL.md).
  • Boundary markers: Absent. The skill does not wrap external content in delimiters or provide instructions to ignore embedded commands.
  • Capability inventory: The skill is limited to reading and writing Markdown and YAML files in specified local directories. It has no network, subprocess, or dynamic execution capabilities (SKILL.md).
  • Sanitization: No sanitization or validation of the external content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:58 PM
Security Audit — agent-trust-hub — flashcards