gen-ai-use
Fail
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides installation instructions that involve downloading a shell script from the author's official domain (https://picsart.com/gen-ai-cli/install.sh) and executing it directly via piped bash.- [DATA_EXFILTRATION]: The CLI tool manages sensitive authentication tokens stored locally in ~/.gen-ai/credentials.json and supports credential injection via environment variables for automated environments.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points: The tool reads prompts from external files via the --prompt-file flag and through standard input piping (ADVANCED.md). Boundary markers: No delimiters or instructions to ignore embedded commands are specified in the provided documentation. Capability inventory: The tool can perform network API calls, upload/download files to Picsart Drive, and write output locally (DRIVE.md, SKILL.md). Sanitization: No validation or escaping of external content before prompt interpolation is described.- [COMMAND_EXECUTION]: The shell completion setup utilizes the eval command to execute dynamically generated code for bash, zsh, and fish shells.
Recommendations
- HIGH: Downloads and executes remote code from: https://picsart.com/gen-ai-cli/install.sh - DO NOT USE without thorough review
Audit Metadata