osxquery
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to interact with the host system using the
osxCLI and thescreencaptureutility for UI automation and state verification as described inSKILL.mdand the usage references. - [DATA_EXFILTRATION]: Functional risk of sensitive data exposure through UI scraping and desktop screenshots. The
osx queryandreadcommands allow the agent to extract text and attributes from any active application window, and thescreencapturepolicy inSKILL.mdcan capture personal or confidential information visible on screen. - [PROMPT_INJECTION]: Vulnerable to indirect prompt injection due to the processing of untrusted host data. 1. Ingestion points: Results from
osx queryand attribute reading found inreferences/osxquery-query-usage.md. 2. Boundary markers: Absent; no specific delimiters or instructions exist to separate UI content from system instructions. 3. Capability inventory: High impact capabilities including typing, clicks, and application lifecycle management viaosx action. 4. Sanitization: Absent; no filtering or escaping of UI-ingested text is prescribed.
Audit Metadata