Skills
skills/openclaw/agent-skills/session-viewer/Gen Agent Trust Hub

session-viewer

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: Spawns platform-specific commands (open on macOS, start on Windows, and xdg-open on Linux) to automatically open the generated HTML session report in the user's default browser.
  • [DATA_EXPOSURE]: Reads local agent session data from standard application paths (e.g., ~/.claude/projects, ~/.codex/sessions) to facilitate visualization and search. This behavior is consistent with the skill's primary purpose.
  • [SAFE]: The skill generates self-contained HTML files using proper escaping for session data to prevent injection issues in the viewer. It does not perform unauthorized network requests or access sensitive system credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 01:56 PM
Security Audit — agent-trust-hub — session-viewer