generate-image

Warn

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill constructs a bash command using the uv run python command and interpolates user-provided text ({{arg:1}}) directly into the command string. If a user provides input containing shell metacharacters or escapes the double quotes (e.g., " ; dangerous_command ; "), it could lead to arbitrary command execution.
  • [PROMPT_INJECTION]: The skill processes untrusted user input that is then interpolated into a command-line interface, creating an indirect injection surface. There are no boundary markers or explicit instructions to the agent to sanitize or ignore malicious sequences in the input.
  • Ingestion points: Image description from {{arg:1}}.
  • Boundary markers: User input is wrapped in double quotes in the shell command, which does not prevent command substitution or escaping.
  • Capability inventory: Access to Bash for command execution and WebFetch for potential data exfiltration.
  • Sanitization: No sanitization or input validation logic is present in the skill instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 13, 2026, 09:54 PM
Security Audit — agent-trust-hub — generate-image