dev-test-hammerspoon

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Hammerspoon CLI (hs) and cliclick to execute Lua scripts and shell commands for UI automation, window management, and process control.
  • [DATA_EXFILTRATION]: The skill captures screenshots using screencapture and reads clipboard contents via hs.pasteboard.getContents(). While these access potentially sensitive data, they are used locally for testing verification as described in the skill's purpose.
  • [REMOTE_CODE_EXECUTION]: The skill executes Lua code dynamically via hs -c and runs local script files. This dynamic execution is a core feature of the Hammerspoon integration and does not involve fetching code from remote untrusted sources.
  • [PROMPT_INJECTION]: The skill reads window titles, menu items, and clipboard contents which could potentially contain malicious instructions (indirect prompt injection) if the application being tested is attacker-controlled. However, the risk is mitigated by the manual testing context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 06:29 AM
Security Audit — agent-trust-hub — dev-test-hammerspoon