image-generation

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-defined prompts for image generation, establishing a surface for indirect prompt injection if input is derived from untrusted sources.\n
  • Ingestion points: User prompts defined in SKILL.md and SKILL.toon.\n
  • Boundary markers: Absent from the instruction templates.\n
  • Capability inventory: Command execution via Bash and file creation via Write tools.\n
  • Sanitization: No sanitization or validation of the prompt string is performed within the skill logic.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool to run commands such as claude mcp list and ask-gemini to manage the environment and perform image generation. These are typical operational commands for the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 04:49 AM