macos-safari
Warn
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill accesses highly sensitive local databases and files related to the user's web browsing activity.
- Evidence: The skill provides commands to read
~/Library/Safari/History.dbusingsqlite3to extract visit titles and URLs. - Evidence: The skill converts and searches
~/Library/Safari/Bookmarks.plistusingplutil, exposing user bookmarks. - [COMMAND_EXECUTION]: The skill makes extensive use of system utilities to control applications and manipulate data.
- Evidence: Uses
osascriptto drive Safari automation, which includes the capability todo JavaScript, allowing for arbitrary code execution within the context of any open web page. - Evidence: Uses
screencaptureto take screenshots of the browser window, which may contain sensitive information. - Evidence: Uses
sqlite3andplutilto interact with system files and databases. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it ingests and processes untrusted data from external websites.
- Ingestion points:
scripts/tab/source.applescript(fetches raw HTML source) andscripts/javascript/run.applescript(fetches page text). - Boundary markers: None identified; the skill returns raw content from the browser directly to the agent's context.
- Capability inventory: Access to system-level automation via AppleScript, the ability to read private browser data (history/bookmarks), and the ability to perform actions in the browser (JS execution).
- Sanitization: No sanitization, filtering, or validation is performed on the content retrieved from web pages before it is processed by the agent.
Audit Metadata