preview-shots
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
opencommand and AppleScript viaosascriptto interact with the macOS Preview application. - [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for command injection if untrusted file paths are processed.
- Ingestion points: Absolute or repo-root-relative file paths for image artifacts (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: Shell command execution using
openand AppleScript execution viaosascript(SKILL.md). - Sanitization: Absent; the instructions do not require the agent to sanitize or escape file paths before passing them to the shell.
Audit Metadata