sn-ppt-workbench

Fail

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: HIGHDATA_EXFILTRATIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [DATA_EXFILTRATION]: Accesses sensitive configuration files. The script scripts/open_workbench.py reads ~/.hermes/.env and other platform-specific environment files to extract authentication secrets such as API_SERVER_KEY and WORKBENCH_GATEWAY_API_KEY.
  • [COMMAND_EXECUTION]: Executes code from unverified local paths. The skill implements a search heuristic in scripts/open_workbench.py that identifies and runs Node.js scripts found in user directories like ~/Repository/ using subprocess.run().
  • [COMMAND_EXECUTION]: Spawns detached background processes. The Node.js launcher workbench-runtime/bin/sensenova-ppt-workbench.mjs uses spawn with detached: true to run a server in the background, which can be used to maintain persistence of unauthorized processes.
  • [CREDENTIALS_UNSAFE]: Hardcoded default credential. The launcher code in sensenova-ppt-workbench.mjs contains a hardcoded fallback API key ppt-editor-dev used for session authentication.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 30, 2026, 08:43 PM
Security Audit — agent-trust-hub — sn-ppt-workbench