experience-lwc-runtime-observe

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local commands using the Salesforce CLI (sf) and Python3 for DOM processing. These are standard developer tools required for the skill's primary purpose of Salesforce development.
  • [DATA_EXPOSURE]: The skill demonstrates high security awareness regarding authentication tokens. It explicitly forbids the agent from running sf org open directly (which would leak a session token to the chat history). Instead, it uses scripts/open-frontdoor.sh to capture the token into a chmod 600 (user-only) temporary file, which is then consumed by the browser driver and deleted immediately.
  • [REMOTE_CODE_EXECUTION]: No external code is downloaded or executed. All logic is contained within the bundled shell and Python scripts provided in the skill package.
  • [PROMPT_INJECTION]: No malicious prompt injection patterns or attempts to override system safety guidelines were detected in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 12:16 PM
Security Audit — agent-trust-hub — experience-lwc-runtime-observe