generate-image
Warn
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: MEDIUMPROMPT_INJECTIONSAFE
Full Analysis
- [PROMPT_INJECTION]: The skill metadata in SKILL.md identifies the author as 'K-Dense Inc.', which conflicts with the provided account context 'Oceanjackson1'. Misleading metadata can be used to misrepresent the origin of a skill.
- [SAFE]: The script scripts/generate_image.py performs network operations to openrouter.ai, a well-known service provider, which is consistent with the skill's intended purpose.
- [SAFE]: Authentication is handled by reading the OPENROUTER_API_KEY from environment variables or a local .env file, adhering to standard security practices for managing secrets.
- [SAFE]: The skill processes user-supplied image prompts. While these are passed to an external API, the risk of indirect prompt injection is minimal given the specialized nature of image generation models. -- Ingestion points: User-supplied prompt argument in scripts/generate_image.py. -- Boundary markers: None present; the prompt is passed directly to the API payload. -- Capability inventory: Network connectivity to openrouter.ai and local file system access for reading and writing images. -- Sanitization: No sanitization or escaping is performed on the input prompt.
Audit Metadata