workspace-layout

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for using standard system utilities such as ls, cat, grep, jq, and find to explore a relayfile mount. These tools are used for their intended purpose of navigating directories and reading metadata files like LAYOUT.md to understand the workspace structure.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to help agents locate and read external data resources (Notion pages, Linear issues, etc.) which could theoretically contain malicious instructions. However, the skill restricts its guidance to discovery and metadata inspection using read-only tools, providing no instructions for high-risk operations such as network exfiltration or file modification based on that data.
  • Ingestion points: File reads from the $MOUNT directory (SKILL.md).
  • Boundary markers: None.
  • Capability inventory: Navigation and search utilities (cat, ls, grep, jq, find) are the only capabilities utilized.
  • Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 10:32 PM
Security Audit — agent-trust-hub — workspace-layout