image-prompt-generator

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script scripts/images/generate_image.py to perform image generation and editing tasks. These commands include user-provided strings as arguments, which can be risky if the underlying script implementation does not perform rigorous input validation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (image prompts and external images) and incorporates it into the agent's execution flow.
  • Ingestion points: User-supplied topics, prompts, and photos (potentially from Telegram as referenced in references/styles/schematic.md) are used as inputs for the generation script.
  • Boundary markers: The instructions lack explicit boundary markers or warnings to prevent the agent from obeying instructions embedded within user-provided prompts.
  • Capability inventory: The skill possesses the capability to execute shell commands, perform network requests via the Gemini API, and read/write files on the local system.
  • Sanitization: No sanitization or shell-escaping mechanisms are described in the instructions to protect against malicious input being executed as part of the command-line arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 11:39 AM
Security Audit — agent-trust-hub — image-prompt-generator