client-workspace

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs local filesystem management tasks, including directory creation and file copying to set up standardized client workspaces. These operations target the local clients/ directory and a vendor-specific configuration path (~/.claude/plugins/config/claude-for-accounting/) to manage client data. These actions are confined to the local environment and align with the skill's primary purpose.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing external files from user-defined paths or the current working directory during the organization and inventory process.
  • Ingestion points: Local files discovered and read during the 'Discovery' and 'Inventory' phases as described in SKILL.md.
  • Boundary markers: No specific boundary markers or explicit safety instructions are defined to isolate the content of processed documents from the agent's logic during the organization workflow.
  • Capability inventory: The skill utilizes file system tools for directory creation, file copying, and writing registration logs (source/register.md).
  • Sanitization: No sanitization or validation mechanisms are mentioned for the content of files before they are processed by the agent for classification and registration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 02:13 PM
Security Audit — agent-trust-hub — client-workspace