screenshot
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script executes the native macOS
screencaptureutility to capture screen content. It also utilizes standard system utilities includingjqfor input parsing,datefor timestamp generation, andsleepfor the delay feature.- [PROMPT_INJECTION]: Indirect prompt injection surface analysis: - Ingestion points: User-provided parameters
type,filename, anddelayare processed from the agent's context inSKILL.md. - Boundary markers: No explicit boundary markers or "ignore instructions" delimiters are used for parameter interpolation.
- Capability inventory: The skill has the capability to execute shell commands and write files to the local file system as defined in
screenshot_cli.sh. - Sanitization: Input parameters are extracted via
jq -rand are properly quoted within the shell script to prevent simple command injection attacks.
Audit Metadata